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

    Neuronpedia

    INDEX
    Explanations

    names containing the syllable "ya"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific name or term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yright
    -0.77
    igree
    -0.73
    drawn
    -0.73
    insula
    -0.70
    starter
    -0.69
    olation
    -0.68
    matically
    -0.67
    deck
    -0.66
    lay
    -0.66
    rers
    -0.65
    POSITIVE LOGITS
     Pradesh
    1.00
     Sabha
    0.95
    zza
    0.86
     Yug
    0.85
    ishi
    0.81
    ya
    0.81
    kees
    0.79
    aaaa
    0.78
    eda
    0.78
     Nik
    0.78
    Act Density 0.006%

    No Known Activations