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

    Neuronpedia

    INDEX
    Explanations

    the presence of numerical values or decimal points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĤa
    -0.16
    ix
    -0.15
    gress
    -0.15
    yre
    -0.15
    ed
    -0.15
    100
    -0.14
    ume
    -0.14
    iera
    -0.14
    errat
    -0.14
    illon
    -0.14
    POSITIVE LOGITS
    foy
    0.16
    rough
    0.16
    jpg
    0.15
     Deck
    0.15
    pdf
    0.15
    obi
    0.15
    cly
    0.15
     Dial
    0.14
    istrovstvÃŃ
    0.14
    istrov
    0.14
    Act Density 0.062%

    No Known Activations