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

    Neuronpedia

    INDEX
    Explanations

    instances of agreement or consent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollen
    -0.15
    urry
    -0.15
    irst
    -0.15
     Samar
    -0.15
    ضاء
    -0.15
    ressing
    -0.14
    ori
    -0.14
    iff
    -0.14
    317
    -0.14
    ething
    -0.14
    POSITIVE LOGITS
    ä¿Ĺ
    0.15
    ILT
    0.14
    ably
    0.14
     Kis
    0.14
    istrovstvÃŃ
    0.14
    baum
    0.13
    ilver
    0.13
    bsolute
    0.13
    ево
    0.13
    ured
    0.13
    Act Density 0.040%

    No Known Activations