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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly in the context of their roles or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.11
    3:0.02
    4:0.03
    5:0.09
    6:0.13
    7:0.12
    8:0.05
    9:0.03
    10:0.09
    11:0.23
    Negative Logits
     illeg
    -1.49
    ?]
    -1.37
     fallacy
    -1.37
    ]).
    -1.37
     caliphate
    -1.37
     unpop
    -1.36
    ".[
    -1.32
     Apocalypse
    -1.31
     disregard
    -1.29
    ][/
    -1.28
    POSITIVE LOGITS
     Lau
    1.57
    antz
    1.54
    enberg
    1.50
    leck
    1.46
    itsch
    1.45
    ansky
    1.44
    hov
    1.39
    cu
    1.35
    ritz
    1.35
    lund
    1.34
    Act Density 0.136%

    No Known Activations