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

    Neuronpedia

    INDEX
    Explanations

    relevant numerical values or measurements within the text, such as quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, specifically related to measurements or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ugal
    -0.93
    acia
    -0.75
    unes
    -0.73
    emade
    -0.73
    swick
    -0.72
    unal
    -0.72
    coat
    -0.71
    munition
    -0.70
    icial
    -0.70
    inges
    -0.69
    POSITIVE LOGITS
     ILCS
    0.91
    MHz
    0.75
     MHz
    0.74
    6666
    0.73
     Rue
    0.72
    px
    0.72
     calories
    0.68
    490
    0.68
     needles
    0.67
    789
    0.67
    Act Density 0.062%

    No Known Activations