Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that denote an overall assessment or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ker
    -0.16
    pond
    -0.16
    ãn
    -0.16
    ess
    -0.15
    ellery
    -0.14
    apore
    -0.14
    ovsky
    -0.14
    ære
    -0.14
    isco
    -0.14
    sport
    -0.14
    POSITIVE LOGITS
    iese
    0.16
    ingham
    0.15
    /down
    0.15
    iz
    0.15
    enga
    0.15
    MENT
    0.14
    most
    0.14
    asel
    0.14
    iss
    0.14
    -purpose
    0.13
    Act Density 0.015%

    No Known Activations