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

    Neuronpedia

    INDEX
    Explanations

    instances of asterisks, likely indicating comments or notes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uman
    -0.19
    iasm
    -0.15
    endoza
    -0.15
    ump
    -0.14
    ilm
    -0.14
    .BatchNorm
    -0.14
    pid
    -0.13
    ANEL
    -0.13
    allas
    -0.13
    919
    -0.13
    POSITIVE LOGITS
    iyon
    0.15
    htags
    0.15
    érique
    0.14
    нÑĭ
    0.14
    æĥł
    0.14
    (#)
    0.14
     sovereign
    0.14
    Ïĥή
    0.13
     Lust
    0.13
    ints
    0.13
    Act Density 0.021%

    No Known Activations