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

    Neuronpedia

    INDEX
    Explanations

    phrases that express conditions or specifications regarding actions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornings
    -0.16
     Há»ĵng
    -0.15
     ************************************************************************
    -0.14
    azor
    -0.14
    ermal
    -0.13
    ertiary
    -0.13
     Lingu
    -0.13
    ote
    -0.13
     Stub
    -0.13
    named
    -0.13
    POSITIVE LOGITS
    ocl
    0.16
    ACL
    0.15
    815
    0.15
    ANJI
    0.14
    Pie
    0.14
    dÃŃ
    0.13
     Pie
    0.13
    arkin
    0.13
    Č↵
    0.13
    andır
    0.13
    Act Density 0.114%

    No Known Activations