© 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. 2301
    Prev
    Next
    INDEX
    Explanations

    expressions of hope or wishful thinking

    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
     confir
    -0.73
    ingham
    -0.65
     WARN
    -0.65
    ieu
    -0.63
     Citation
    -0.62
     Explain
    -0.62
    imo
    -0.62
    Exc
    -0.61
     congratulations
    -0.59
     challeng
    -0.59
    POSITIVE LOGITS
    pak
    0.68
    bottom
    0.68
    years
    0.66
    enses
    0.65
    weapon
    0.63
     Mercenary
    0.62
    nothing
    0.62
    comes
    0.61
     ruins
    0.61
     decades
    0.61
    Activations Density 0.118%

    No Known Activations