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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undy
    -0.18
    ód
    -0.16
    esser
    -0.16
    оном
    -0.15
     Compliance
    -0.15
    aph
    -0.15
    è£
    -0.14
    Ùģات
    -0.14
    appa
    -0.14
    IGO
    -0.14
    POSITIVE LOGITS
    opc
    0.14
     vac
    0.14
    opo
    0.14
    upe
    0.14
    ipeg
    0.13
     Roc
    0.13
    arent
    0.13
     Jac
    0.13
    á»įc
    0.13
     éĽ
    0.13
    Act Density 0.212%

    No Known Activations