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

    Neuronpedia

    INDEX
    Explanations

    dates written in a specific format, possibly within a sequence, such as dates at the beginning or end of a segment of text

    oai_token-act-pair · gpt-3.5-turbo

    numeric data and references to specific entities or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.73
    ."[
    -0.71
    .")
    -0.69
    .'"
    -0.68
    !'"
    -0.67
    stro
    -0.66
    ");
    -0.64
    ".[
    -0.62
    redo
    -0.62
    ocations
    -0.61
    POSITIVE LOGITS
     autos
    0.66
     Located
    0.65
     âĵĺ
    0.62
    aea
    0.61
     hers
    0.60
     Koen
    0.60
    ĪĴ
    0.60
    ?????-
    0.59
     TBD
    0.58
     Ember
    0.58
    Act Density 0.778%

    No Known Activations