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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing attention to individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.08
    3:0.08
    4:0.18
    5:0.02
    6:0.05
    7:0.32
    8:0.03
    9:0.04
    10:0.06
    11:0.05
    Negative Logits
    imester
    -1.64
     expires
    -1.61
     financed
    -1.59
     orbit
    -1.52
     funded
    -1.48
     immortality
    -1.43
     tenure
    -1.42
     means
    -1.39
     govern
    -1.39
     odds
    -1.37
    POSITIVE LOGITS
    zsche
    1.78
    abel
    1.63
    zl
    1.54
     anecd
    1.54
    cape
    1.53
     notices
    1.52
    dog
    1.50
    cham
    1.49
    issues
    1.49
     atrocities
    1.42
    Act Density 0.000%

    No Known Activations