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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to groups and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.11
    1:0.06
    2:0.01
    3:0.13
    4:0.10
    5:0.13
    6:0.06
    7:0.04
    8:0.19
    9:0.08
    10:0.01
    11:0.02
    Negative Logits
     tainted
    -2.04
     merged
    -1.94
     electronically
    -1.87
     digitally
    -1.80
     arsen
    -1.79
     TNT
    -1.73
     emitting
    -1.72
     tint
    -1.70
     VS
    -1.69
     tampering
    -1.67
    POSITIVE LOGITS
    rities
    2.77
    arters
    2.35
    abies
    2.18
    ynes
    2.17
    erning
    1.98
    iences
    1.97
    Case
    1.93
    ptions
    1.93
    forts
    1.90
    ividual
    1.89
    Act Density 0.000%

    No Known Activations