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

    Neuronpedia

    INDEX
    Explanations

    conversational exchanges and emotional interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anter
    -0.16
    acak
    -0.15
    زÙĨ
    -0.15
     DEFINE
    -0.15
     preca
    -0.14
    otime
    -0.14
    _DYNAMIC
    -0.14
    *);↵↵
    -0.13
    quisa
    -0.13
    prise
    -0.13
    POSITIVE LOGITS
     decide
    0.23
     decided
    0.22
     decides
    0.21
    äºİæĺ¯
    0.20
     automatically
    0.18
     began
    0.17
     abandoned
    0.17
     decision
    0.17
    ument
    0.16
     immediate
    0.16
    Act Density 0.261%

    No Known Activations