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

    Neuronpedia

    INDEX
    Explanations

    information related to specific years and events

    oai_token-act-pair · gpt-3.5-turbo

    commas in lists or sequences within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dialog
    -0.66
    ¬¼
    -0.65
    alogy
    -0.63
     interaction
    -0.62
    eries
    -0.62
    natureconservancy
    -0.62
    atio
    -0.60
    hed
    -0.59
    tro
    -0.59
    irc
    -0.57
    POSITIVE LOGITS
     respectively
    0.96
     although
    0.90
     according
    0.90
     culminating
    0.78
     namely
    0.77
     graduating
    0.76
    etheus
    0.75
     citing
    0.75
     onwards
    0.73
     albeit
    0.73
    Act Density 0.421%

    No Known Activations