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

    Neuronpedia

    INDEX
    Explanations

    emotional responses and reactions in dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ASSUME
    -0.15
    dit
    -0.15
    ModelIndex
    -0.14
    åĦĢ
    -0.14
    hint
    -0.14
    iring
    -0.14
     Vick
    -0.14
     Cutting
    -0.14
    оÑĩка
    -0.14
    ento
    -0.13
    POSITIVE LOGITS
     immediately
    0.22
     immediate
    0.21
     instantly
    0.21
     reaction
    0.19
     ç«ĭ
    0.17
     instantaneous
    0.17
     instant
    0.17
     immedi
    0.17
    mediately
    0.16
     reactions
    0.16
    Act Density 0.256%

    No Known Activations