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

    Neuronpedia

    INDEX
    Explanations

    phrases that assess the general quality or effectiveness of various subjects or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pond
    -0.16
    ervlet
    -0.16
    ambre
    -0.15
    .stock
    -0.15
    blade
    -0.14
    /problem
    -0.14
    ализи
    -0.14
    eth
    -0.14
    SZ
    -0.14
    бов
    -0.14
    POSITIVE LOGITS
    Invariant
    0.17
    iese
    0.16
    ÑĢÑĮ
    0.15
    /down
    0.15
    ingham
    0.15
    ĭ
    0.15
    ipc
    0.15
    mac
    0.14
    ÃŃ
    0.14
    stay
    0.14
    Act Density 0.011%

    No Known Activations