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

    Neuronpedia

    INDEX
    Explanations

    terms related to medical conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.36
    1:0.04
    2:0.01
    3:0.11
    4:0.11
    5:0.09
    6:0.03
    7:0.02
    8:0.09
    9:0.06
    10:0.01
    11:0.01
    Negative Logits
    today
    -1.61
     Burma
    -1.60
    ryu
    -1.58
    ixir
    -1.57
    uesday
    -1.57
     Yankee
    -1.53
     courage
    -1.53
     Wer
    -1.52
     tomorrow
    -1.52
    ffee
    -1.51
    POSITIVE LOGITS
    multiple
    2.33
    alities
    2.17
    Multiple
    2.09
     mutually
    2.09
     Multiple
    2.04
     simultaneous
    2.03
     extremes
    1.97
    artments
    1.96
    lections
    1.94
    iblings
    1.93
    Act Density 0.027%

    No Known Activations