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

    Neuronpedia

    INDEX
    Explanations

    punctuation, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.08
    3:0.08
    4:0.09
    5:0.07
    6:0.09
    7:0.07
    8:0.07
    9:0.09
    10:0.06
    11:0.08
    Negative Logits
     Oliver
    -3.30
     Citizenship
    -3.18
     Palmer
    -3.14
     Commissioner
    -2.96
     Lois
    -2.94
     Pal
    -2.89
     Rosenthal
    -2.83
     Wil
    -2.82
     Stein
    -2.79
     Card
    -2.79
    POSITIVE LOGITS
    pex
    3.26
    obyl
    2.98
    hetamine
    2.88
    achev
    2.87
    okane
    2.80
    inki
    2.74
    urnal
    2.71
    enf
    2.70
    zees
    2.69
    hent
    2.63
    Act Density 0.000%

    No Known Activations