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

    Neuronpedia

    INDEX
    Explanations

    specific special characters and phrases that include them

    oai_token-act-pair · gpt-3.5-turbo

    references or symbols related to a specific individual or character in a repeated manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.72
     multiplying
    -0.69
     Sylvia
    -0.67
     assassinate
    -0.66
     specificity
    -0.65
     fulfillment
    -0.64
    redients
    -0.64
     travel
    -0.63
     confinement
    -0.62
     blacklist
    -0.62
    POSITIVE LOGITS
    ¬
    1.07
    º
    1.05
    į
    1.04
    ı
    1.03
    ¹
    1.00
    ł
    0.98
    Ĵ
    0.98
    Ń
    0.96
    §
    0.95
    Ľ
    0.93
    Act Density 0.061%

    No Known Activations