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

    Neuronpedia

    INDEX
    Explanations

    cyrillic characters related to electrical grids

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     traff
    -0.71
    ifact
    -0.71
    ainer
    -0.69
     GOODMAN
    -0.66
    ifully
    -0.66
    emort
    -0.65
    iants
    -0.65
    iewicz
    -0.65
    istically
    -0.65
    iful
    -0.64
    POSITIVE LOGITS
    л
    1.01
    в
    1.01
    н
    0.95
    д
    0.93
    м
    0.90
    0.87
    Ñı
    0.87
    ر
    0.85
    Ð
    0.81
    ãĤ§
    0.80
    Act Density 0.021%

    No Known Activations