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

    Neuronpedia

    INDEX
    Explanations

    words related to physical strength or power

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurement, classification, and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANA
    -0.68
    Snow
    -0.64
    Cons
    -0.63
    Nap
    -0.62
    STR
    -0.60
    itness
    -0.59
    pmwiki
    -0.58
    Int
    -0.58
    HEAD
    -0.56
    itta
    -0.56
    POSITIVE LOGITS
    of
    1.06
     of
    1.04
     OF
    0.94
     thereof
    0.90
    )=(
    0.80
     Of
    0.80
    Of
    0.79
    ãĤ´ãĥ³
    0.75
    uary
    0.73
    oft
    0.70
    Act Density 0.191%

    No Known Activations