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

    Neuronpedia

    INDEX
    Explanations

    tokens that denote the start of a document and special formatting or structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelSerializer
    -0.53
    henko
    -0.52
    κα
    -0.51
    ’
    -0.51
    ,
    -0.49
    伍
    -0.49
    ii
    -0.48
    1
    -0.47
    “
    -0.47
    ValueStyle
    -0.47
    POSITIVE LOGITS
     betweenstory
    0.99
    Tikang
    0.89
    хьтан
    0.88
    0.85
     disambiguazione
    0.84
    *{-
    0.80
    ########.
    0.77
    Rüyada
    0.76
    tvguidetime
    0.76
     мәкал
    0.75
    Act Density 0.064%

    No Known Activations