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

    Neuronpedia

    INDEX
    Explanations

    names of people or roles in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in specific roles or occupations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    english
    -0.69
    edIn
    -0.68
    اÙĦ
    -0.64
    ourced
    -0.60
    iege
    -0.58
    ourcing
    -0.58
    ystem
    -0.56
    Cover
    -0.54
    poons
    -0.54
    iHUD
    -0.54
    POSITIVE LOGITS
     himself
    1.11
    's
    1.00
     Himself
    0.89
    osphere
    0.88
     whom
    0.86
    owicz
    0.81
     who
    0.80
    digy
    0.78
     herself
    0.71
    who
    0.71
    Act Density 0.178%

    No Known Activations