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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating recent actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uder
    -0.14
    ÑĩиÑģ
    -0.14
     xmm
    -0.14
    830
    -0.14
    aty
    -0.14
     ()->
    -0.14
     impression
    -0.13
     ti
    -0.13
    ाड
    -0.13
    -wise
    -0.13
    POSITIVE LOGITS
     recently
    0.19
     finished
    0.18
    lint
    0.15
    urope
    0.15
     finish
    0.15
    endor
    0.15
     xong
    0.15
     newly
    0.15
     Forbidden
    0.15
    åĪļ
    0.14
    Act Density 0.081%

    No Known Activations