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

    Neuronpedia

    INDEX
    Explanations

    terms that indicate confusion or misrepresentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iger
    -0.16
    implify
    -0.16
    aylight
    -0.15
    ìĦ¸ëĮĢ
    -0.15
    à¥Įत
    -0.14
    andas
    -0.14
    ivot
    -0.14
    andal
    -0.14
    µ
    -0.14
    ÙĤØ·
    -0.14
    POSITIVE LOGITS
    062
    0.16
    638
    0.14
    ér
    0.14
    inan
    0.14
    ìĽ
    0.14
    _hint
    0.14
    atem
    0.14
    emodel
    0.14
    ÅĦ
    0.13
    698
    0.13
    Act Density 0.000%

    No Known Activations