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

    Neuronpedia

    INDEX
    Explanations

    people's names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wilmington
    -0.78
     barn
    -0.78
     Aber
    -0.78
     Chester
    -0.77
     UPS
    -0.77
     Barn
    -0.75
     Goose
    -0.73
     Wald
    -0.73
     Hunts
    -0.73
     Beaver
    -0.73
    POSITIVE LOGITS
    mi
    1.45
    ati
    1.37
    ni
    1.36
    ti
    1.35
    gi
    1.31
    ori
    1.31
    ali
    1.31
    ari
    1.29
    ici
    1.29
    adi
    1.29
    Act Density 0.337%

    No Known Activations