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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or conditions between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Fah
    -0.16
    apot
    -0.15
    _integration
    -0.15
    jit
    -0.14
     violation
    -0.14
     violations
    -0.14
    fen
    -0.14
     zast
    -0.14
     Pais
    -0.13
     京
    -0.13
    POSITIVE LOGITS
    erb
    0.18
    ADB
    0.16
    usta
    0.15
    ÏĥÏĦαν
    0.15
     Chief
    0.15
    ungle
    0.15
    dej
    0.15
    stantiate
    0.14
    cki
    0.14
    صÙĩ
    0.14
    Act Density 0.055%

    No Known Activations