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

    Neuronpedia

    INDEX
    Explanations

    fractions or numerical expressions indicating division

    oai_token-act-pair · gpt-3.5-turbo

    references to fractional quantities or proportions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     arrang
    -0.75
     showc
    -0.74
     mathemat
    -0.70
     Mahar
    -0.68
    Matrix
    -0.66
     toget
    -0.65
     captcha
    -0.64
     pastoral
    -0.64
    BALL
    -0.63
     introdu
    -0.63
    POSITIVE LOGITS
    ousand
    0.86
     percent
    0.78
    million
    0.77
    +)
    0.76
     Nieto
    0.75
    ority
    0.74
    billion
    0.73
    uary
    0.71
    ilion
    0.71
    undred
    0.70
    Act Density 0.061%

    No Known Activations