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

    Neuronpedia

    INDEX
    Explanations

    names and titles of public figures

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles of individuals in positions of authority or leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     VIDEOS
    -0.70
     ACTIONS
    -0.64
    tnc
    -0.64
    IRE
    -0.63
    articles
    -0.62
     Matters
    -0.59
     guiActiveUnfocused
    -0.57
     UNIVERS
    -0.56
    ALLY
    -0.56
    LESS
    -0.56
    POSITIVE LOGITS
     overseeing
    0.93
     whom
    0.91
     extraord
    0.90
     credited
    0.87
     presiding
    0.85
     who
    0.85
     pictured
    0.83
     responsible
    0.83
     whose
    0.81
     tasked
    0.78
    Act Density 0.181%

    No Known Activations