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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating reactions or responses to various situations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icago
    -0.15
    igi
    -0.15
    ÑĢиз
    -0.15
    clid
    -0.15
    otte
    -0.14
    xing
    -0.14
    véd
    -0.14
    inki
    -0.14
    Ñijм
    -0.14
    deo
    -0.14
    POSITIVE LOGITS
    ivate
    0.18
    aries
    0.17
    /response
    0.16
    ant
    0.15
    ÂŃs
    0.15
    -response
    0.15
    ToSelector
    0.15
    idual
    0.14
    ä¸įäºĨ
    0.14
     manner
    0.14
    Act Density 0.054%

    No Known Activations