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

    Neuronpedia

    INDEX
    Explanations

    names containing the string "bie"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the suffix 'bie' and related words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agonist
    -0.78
    ators
    -0.76
    ifer
    -0.76
    ively
    -0.73
    uality
    -0.72
    overs
    -0.72
    ors
    -0.71
    igator
    -0.68
    ibal
    -0.67
    context
    -0.66
    POSITIVE LOGITS
    GES
    0.92
    bie
    0.90
    glers
    0.86
    gee
    0.82
    ertodd
    0.77
    llan
    0.76
    lly
    0.75
    bies
    0.72
    yond
    0.71
    ellow
    0.71
    Act Density 0.027%

    No Known Activations