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

    Neuronpedia

    INDEX
    Explanations

    articles and proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.35
    1:0.01
    2:0.01
    3:0.03
    4:0.04
    5:0.09
    6:0.04
    7:0.02
    8:0.29
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
    chenko
    -2.24
    iann
    -1.91
    yss
    -1.91
    vous
    -1.85
    hib
    -1.84
    ydia
    -1.80
    emis
    -1.77
    hooting
    -1.74
    vae
    -1.74
    obyl
    -1.73
    POSITIVE LOGITS
     victory
    1.89
     ®
    1.83
     ensued
    1.76
     diamond
    1.75
    Winner
    1.69
     prevail
    1.65
     vacated
    1.63
     diamonds
    1.61
     throne
    1.60
     belt
    1.60
    Act Density 0.000%

    No Known Activations