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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to individuals in a political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.09
    3:0.09
    4:0.07
    5:0.08
    6:0.07
    7:0.07
    8:0.09
    9:0.07
    10:0.09
    11:0.08
    Negative Logits
     tradem
    -1.76
    rings
    -1.73
    emia
    -1.72
    etry
    -1.63
     belonged
    -1.61
    ipment
    -1.60
    iture
    -1.58
    orable
    -1.57
     interacted
    -1.56
     theaters
    -1.54
    POSITIVE LOGITS
     Surviv
    1.90
    lda
    1.76
    usterity
    1.73
     hindsight
    1.68
     GOODMAN
    1.68
     upbeat
    1.66
    hander
    1.63
    --------------------
    1.58
     fuss
    1.57
     dearly
    1.57
    Act Density 0.000%

    No Known Activations