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

    Neuronpedia

    INDEX
    Explanations

    numerical values, such as quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical quantities and ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Caption
    -0.66
     Elections
    -0.62
    lected
    -0.58
     Doodle
    -0.57
     Sullivan
    -0.57
     Lie
    -0.55
     Bashar
    -0.55
     Pearson
    -0.54
     Lawson
    -0.54
     visibly
    -0.53
    POSITIVE LOGITS
    -$
    1.21
    +.
    1.05
    dozen
    1.02
    depending
    0.89
     depending
    0.87
    /$
    0.82
    $.
    0.82
     ballpark
    0.79
    +,
    0.78
    yip
    0.78
    Act Density 0.387%

    No Known Activations