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

    Neuronpedia

    INDEX
    Explanations

    specific types of professionals or groups of people, particularly in research contexts

    oai_token-act-pair · gpt-3.5-turbo

    words related to roles or titles of individuals involved in research or academic activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTERS
    -0.73
    DonaldTrump
    -0.71
    BALL
    -0.66
     Cable
    -0.63
    ģ«
    -0.61
    atever
    -0.60
    âĢ¢âĢ¢
    -0.59
    Street
    -0.59
     Technology
    -0.58
    cially
    -0.58
    POSITIVE LOGITS
    folk
    1.02
     themselves
    0.94
    ']
    0.93
    '
    0.88
    hip
    0.78
    ettings
    0.78
    heet
    0.74
    etter
    0.73
     weren
    0.71
    mith
    0.70
    Act Density 0.204%

    No Known Activations