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

    Neuronpedia

    INDEX
    Explanations

    references to academic fields and interdisciplinary studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rip
    -0.16
    iggers
    -0.16
    uke
    -0.14
    inha
    -0.14
    uire
    -0.14
    roid
    -0.14
    oted
    -0.14
    ût
    -0.14
    ure
    -0.13
     Freeze
    -0.13
    POSITIVE LOGITS
    _areas
    0.17
    -specific
    0.15
    /topic
    0.15
     áreas
    0.15
     especÃŃf
    0.14
    üstü
    0.14
     escorte
    0.14
     ÙĨØ´
    0.14
     areas
    0.14
    -domain
    0.14
    Act Density 0.219%

    No Known Activations