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

    Neuronpedia

    INDEX
    Explanations

    references to inhumane or unethical actions and concepts related to hypocrisy and coercion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chartInstance
    -0.15
    ANGER
    -0.14
    InputStream
    -0.14
    EMPL
    -0.14
    IntegerField
    -0.14
    βά
    -0.14
    пон
    -0.14
    ãĥŃãĥ³
    -0.14
    rose
    -0.14
     Guth
    -0.14
    POSITIVE LOGITS
    /out
    0.35
    itably
    0.21
    itable
    0.20
    idual
    0.19
    -Out
    0.19
    ,out
    0.18
    /up
    0.18
    halten
    0.18
    lectual
    0.18
    achment
    0.18
    Act Density 0.089%

    No Known Activations