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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONTAL
    -0.19
    EPROM
    -0.15
    angan
    -0.14
    ifications
    -0.14
    ammen
    -0.14
    avez
    -0.13
    unca
    -0.13
     pragma
    -0.13
    mán
    -0.13
    ác
    -0.13
    POSITIVE LOGITS
    oud
    0.16
    hed
    0.15
    олод
    0.15
    obao
    0.14
    quee
    0.14
    peri
    0.14
    obil
    0.14
     hedge
    0.14
    Chip
    0.14
     Balance
    0.14
    Act Density 0.006%

    No Known Activations