© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1747
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditions or situations where something is achievable or difficult

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     belong
    -0.79
     become
    -0.75
    thinkable
    -0.73
    ctor
    -0.71
     assemble
    -0.70
    ibaba
    -0.70
     participate
    -0.68
     invade
    -0.68
    ividual
    -0.68
     declare
    -0.67
    POSITIVE LOGITS
     doctors
    0.73
     Arabs
    0.73
     us
    0.71
     Israelis
    0.70
     him
    0.69
     people
    0.68
     Greeks
    0.68
     Premiership
    0.67
     Cohen
    0.66
     Rico
    0.66
    Activations Density 0.101%

    No Known Activations