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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and technical terms related to data processing

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and symbols related to data structures and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hap
    -0.76
    google
    -0.71
    uyomi
    -0.63
     Hugo
    -0.63
     GOODMAN
    -0.62
    apeshifter
    -0.62
     Gorge
    -0.61
    ¥µ
    -0.60
    angel
    -0.60
     sus
    -0.59
    POSITIVE LOGITS
    (
    1.20
    (-
    1.16
    (_
    1.09
    ('
    1.01
     (
    0.98
    ())
    0.98
    (\
    0.96
    (&
    0.93
    ([
    0.92
    ("
    0.92
    Act Density 0.152%

    No Known Activations