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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusivity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.07
    4:0.09
    5:0.10
    6:0.08
    7:0.08
    8:0.08
    9:0.06
    10:0.07
    11:0.08
    Negative Logits
     Sasuke
    -2.67
    ————————
    -2.67
    rawn
    -2.64
     Gohan
    -2.60
    �
    -2.59
     Kramer
    -2.56
    vic
    -2.54
    ć
    -2.54
     ±
    -2.54
    �
    -2.53
    POSITIVE LOGITS
     petition
    3.00
     petitions
    2.95
     illegitimate
    2.91
     Privacy
    2.72
     Emblem
    2.67
     Sanctuary
    2.66
     Registry
    2.63
     Owners
    2.58
     Witcher
    2.54
     Petition
    2.54
    Act Density 0.000%

    No Known Activations