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

    Neuronpedia

    INDEX
    Explanations

    various forms of colons and punctuation that introduce lists or sections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ADOR
    -0.16
    bens
    -0.15
    gregar
    -0.15
    lerce
    -0.14
    luet
    -0.14
    ikler
    -0.14
    eler
    -0.14
    buat
    -0.14
    ões
    -0.14
    andan
    -0.14
    POSITIVE LOGITS
    uki
    0.15
    dust
    0.15
    opal
    0.15
    enc
    0.14
    enting
    0.14
     Seeking
    0.14
    ãģĹãģ®
    0.13
     Mort
    0.13
    atten
    0.13
    ater
    0.13
    Act Density 0.002%

    No Known Activations