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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions involving fractions

    oai_token-act-pair · gpt-3.5-turbo

    symbols and punctuation related to graphical or coding elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beir
    -0.92
    nesday
    -0.86
    itionally
    -0.84
    ateurs
    -0.79
    ablishment
    -0.76
    raints
    -0.74
    eele
    -0.73
     Canter
    -0.71
    iguous
    -0.71
    ible
    -0.71
    POSITIVE LOGITS
    cffffcc
    1.07
    NW
    0.92
    76561
    0.88
    cffff
    0.85
    Pg
    0.81
    Mah
    0.81
    Vi
    0.81
    hl
    0.79
    Pref
    0.75
    sa
    0.75
    Act Density 0.006%

    No Known Activations