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

    Neuronpedia

    INDEX
    Explanations

    inconsistent characters or unrecognized text patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    och
    -0.94
    cius
    -0.94
    arton
    -0.88
    onics
    -0.87
    hyde
    -0.85
    anza
    -0.85
    chio
    -0.85
    inar
    -0.83
    achy
    -0.82
    otype
    -0.82
    POSITIVE LOGITS
    ãĤī
    1.44
    ãģĦ
    1.43
    ãģ¾
    1.43
    ãĤ
    1.41
    ãģ
    1.41
    ãģŁ
    1.37
    ãģ¦
    1.34
    ãĤĵ
    1.31
    ãģĵ
    1.29
    ãģĭ
    1.29
    Act Density 0.009%

    No Known Activations