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

    Neuronpedia

    INDEX
    Explanations

    patterns or symbols representing negative values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Hyphens surrounded by various characters

    np_acts-logits-general · gemini-2.0-flash

    code and punctuation fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.88
    —
    -0.72
    Архівовано
    -0.68
    liothèque
    -0.65
     DbContext
    -0.63
     ***!
    -0.63
    ……」
    -0.61
    жки
    -0.60
    〝
    -0.60
    ,
    -0.59
    POSITIVE LOGITS
    ----------------
    1.76
    ---------------
    1.30
    awtextra
    1.15
    //-
    0.96
    &-
    0.94
    .-"
    0.91
     -}
    0.87
    ">-
    0.85
    /-
    0.84
    ˏ
    0.84
    Act Density 0.401%

    No Known Activations