© 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. 2725
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of something or reluctance to provide information

    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
    oğ
    -0.70
    herer
    -0.70
     rather
    -0.69
    combe
    -0.69
    hem
    -0.69
    enery
    -0.68
    Afee
    -0.67
    oso
    -0.66
    chn
    -0.66
    alm
    -0.65
    POSITIVE LOGITS
     anything
    1.01
     any
    0.96
     nor
    0.90
     anymore
    0.87
    anything
    0.78
     ANY
    0.73
     conclusive
    0.72
     substantive
    0.71
     metals
    0.71
     immunity
    0.70
    Activations Density 0.272%

    No Known Activations