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

    Neuronpedia

    INDEX
    Explanations

    references to regulations or regulatory frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     h
    -0.15
    loff
    -0.15
    ijken
    -0.15
    enheim
    -0.15
    orra
    -0.15
     breath
    -0.15
    head
    -0.14
     é¡
    -0.14
    over
    -0.14
    ,
    -0.14
    POSITIVE LOGITS
     occasions
    0.17
     behalf
    0.17
     occasion
    0.16
    .dsl
    0.15
     detriment
    0.15
    /helper
    0.14
    rypton
    0.14
     Ïĥελ
    0.14
    BarButton
    0.14
    lers
    0.13
    Act Density 0.048%

    No Known Activations