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

    Neuronpedia

    INDEX
    Explanations

    discussions on censorship and the challenges faced by writers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avior
    -0.17
    onen
    -0.15
    adius
    -0.14
    ADX
    -0.14
    ovu
    -0.14
    ->
    -0.14
     Monaco
    -0.13
     catalogs
    -0.13
     favorable
    -0.13
     fueled
    -0.13
    POSITIVE LOGITS
     Partition
    0.22
    dal
    0.18
     Dal
    0.17
     Bengal
    0.17
    Dal
    0.16
     pady
    0.16
     Bengals
    0.16
     dal
    0.16
    andal
    0.16
    Partition
    0.16
    Act Density 0.131%

    No Known Activations