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

    Neuronpedia

    INDEX
    Explanations

    references to various media, particularly comics and films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.09
    3:0.06
    4:0.07
    5:0.02
    6:0.09
    7:0.35
    8:0.03
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
    emetery
    -1.60
     subsequ
    -1.60
     arrang
    -1.59
     reservations
    -1.57
     encamp
    -1.53
    �
    -1.53
     landmark
    -1.49
     affili
    -1.44
     bonus
    -1.43
     bonuses
    -1.42
    POSITIVE LOGITS
    chnology
    1.63
    RPG
    1.63
    lance
    1.62
    pour
    1.56
    anguages
    1.50
    aic
    1.45
     Codec
    1.45
    taboola
    1.44
    ="#
    1.44
    vity
    1.44
    Act Density 0.000%

    No Known Activations