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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals, particularly repeating names like "Emanuel" and "Chow."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Emanuel" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rarily
    -0.79
    othal
    -0.75
    ovember
    -0.74
    =-=-=-=-
    -0.72
    secure
    -0.71
    =-=-=-=-=-=-=-=-
    -0.69
    astery
    -0.69
    reading
    -0.69
     Paran
    -0.68
    ysc
    -0.68
    POSITIVE LOGITS
     Emanuel
    1.11
    wald
    0.79
    mann
    0.65
     ANC
    0.65
    guy
    0.64
    cair
    0.62
     Bauer
    0.62
    lem
    0.61
    son
    0.61
    luck
    0.60
    Act Density 0.017%

    No Known Activations