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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs related to describing or defining characteristics or qualities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "character" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IDA
    -0.77
    EMS
    -0.77
    yg
    -0.70
    abouts
    -0.69
    xon
    -0.68
    nesday
    -0.68
    VEN
    -0.65
     Tanz
    -0.64
    scl
    -0.63
    yden
    -0.62
    POSITIVE LOGITS
    istically
    1.71
    istics
    1.68
    izations
    1.50
    izes
    1.34
    isation
    1.27
    isations
    1.25
    izing
    1.17
    ised
    1.15
    istic
    1.12
    istical
    1.11
    Act Density 0.033%

    No Known Activations