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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "wan"

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of a specific name associated with a person in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    £ı
    -0.68
     predictive
    -0.67
    igslist
    -0.65
     leaflets
    -0.65
     liability
    -0.65
    İĭ
    -0.65
     negatives
    -0.64
     glory
    -0.64
     clustered
    -0.64
     plaintiff
    -0.64
    POSITIVE LOGITS
    wan
    1.39
    ovan
    1.07
    igan
    1.04
    wu
    1.03
    hao
    1.03
    awan
    1.02
    athan
    1.00
    igans
    0.95
    aran
    0.89
     Kenobi
    0.88
    Act Density 0.004%

    No Known Activations