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

    Neuronpedia

    INDEX
    Explanations

    actions and events that indicate the beginning or realization of a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     if
    -0.21
     when
    -0.18
     vi
    -0.18
     never
    -0.18
     as
    -0.17
     until
    -0.17
     both
    -0.17
     much
    -0.17
     quite
    -0.16
     Gh
    -0.16
    POSITIVE LOGITS
     _______,
    0.19
    574
    0.17
    ï¼ĮåĪĻ
    0.16
     ÑģÑĤало
    0.16
     thì
    0.15
    maal
    0.15
    755
    0.15
     erotische
    0.15
     ÙģØ¥ÙĨ
    0.15
    ạn
    0.14
    Act Density 0.209%

    No Known Activations