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

    Neuronpedia

    INDEX
    Explanations

    the symbol '/' in measurement units

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of various numeric and measurement formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carlton
    -0.82
    uyomi
    -0.73
     Fletcher
    -0.72
     Faw
    -0.71
     Starr
    -0.70
    >>\
    -0.70
     Pag
    -0.69
     Spiral
    -0.69
     Pyramid
    -0.68
     Burgess
    -0.66
    POSITIVE LOGITS
    etc
    1.15
    oct
    0.99
    acet
    0.97
    1000
    0.94
    CO
    0.91
    PUT
    0.90
    NAT
    0.89
    ISO
    0.87
    CN
    0.87
    UV
    0.86
    Act Density 0.054%

    No Known Activations