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

    Neuronpedia

    INDEX
    Explanations

    dates and times in text format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of slashes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subsequ
    -0.63
     explan
    -0.63
     pneum
    -0.62
     tender
    -0.61
     wagon
    -0.59
    repre
    -0.59
    terday
    -0.59
    axter
    -0.59
     vaguely
    -0.59
    abies
    -0.58
    POSITIVE LOGITS
    ËĪ
    1.46
     Via
    0.97
     Shutterstock
    0.94
    usr
    0.92
    Film
    0.80
    \/\/
    0.80
    u
    0.78
    etc
    0.76
     IMAGES
    0.75
    ãģ¦
    0.74
    Act Density 0.022%

    No Known Activations