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

    Neuronpedia

    INDEX
    Explanations

    references to people's names, potentially in specific contexts like politics or sports

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phonetic component "hr."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    luaj
    -0.66
     conqu
    -0.63
     Flavoring
    -0.63
     Samoa
    -0.62
     redu
    -0.61
     Roosevelt
    -0.60
     listens
    -0.59
     Pok
    -0.58
    eenth
    -0.57
     Prometheus
    -0.57
    POSITIVE LOGITS
    lich
    1.50
    lein
    0.95
    mann
    0.92
    acht
    0.90
    anger
    0.89
    kamp
    0.88
    itage
    0.86
    rr
    0.86
    uty
    0.86
    ich
    0.85
    Act Density 0.021%

    No Known Activations