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

    Neuronpedia

    INDEX
    Explanations

    the word "on"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.07
    3:0.08
    4:0.07
    5:0.07
    6:0.08
    7:0.07
    8:0.09
    9:0.09
    10:0.09
    11:0.08
    Negative Logits
    apest
    -1.95
     ¯
    -1.77
    itors
    -1.73
    agall
    -1.68
    eln
    -1.65
     Tribunal
    -1.63
    zzo
    -1.62
     Poker
    -1.61
    oux
    -1.61
     Gibraltar
    -1.60
    POSITIVE LOGITS
     nausea
    1.69
    Abstract
    1.67
    cause
    1.59
     emergency
    1.59
     divorced
    1.55
     paralyzed
    1.53
    gency
    1.51
    oulder
    1.50
     condemned
    1.49
     denial
    1.49
    Act Density 0.000%

    No Known Activations