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

    Neuronpedia

    INDEX
    Explanations

    terms related to safety regulations and compliance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     xong
    -0.16
    aga
    -0.14
    elden
    -0.14
    agh
    -0.14
    ousel
    -0.14
    ůj
    -0.14
    _vlog
    -0.14
     woke
    -0.14
    AZE
    -0.14
     McCabe
    -0.14
    POSITIVE LOGITS
     being
    0.20
    being
    0.17
     among
    0.16
     chez
    0.15
    361
    0.15
     bagi
    0.15
    çŁ¢
    0.15
    "./
    0.15
    310
    0.15
    ela
    0.14
    Act Density 0.324%

    No Known Activations