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

    Neuronpedia

    INDEX
    Explanations

    words related to personal names

    oai_token-act-pair · gpt-3.5-turbo

    words related to alcoholic beverages or distillation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lance
    -0.84
    awei
    -0.70
    rences
    -0.69
     Seym
    -0.68
    population
    -0.66
    eas
    -0.66
    ingly
    -0.65
    kward
    -0.65
    spin
    -0.64
    aepernick
    -0.64
    POSITIVE LOGITS
    osaurs
    1.03
    ned
    1.02
    ny
    0.98
    fo
    0.97
    ergic
    0.93
    eman
    0.92
    strument
    0.91
    itis
    0.90
    jad
    0.85
    igans
    0.84
    Act Density 0.148%

    No Known Activations