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

    Neuronpedia

    INDEX
    Explanations

    prominent figures or individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.13
    2:0.03
    3:0.04
    4:0.04
    5:0.31
    6:0.02
    7:0.01
    8:0.07
    9:0.12
    10:0.09
    11:0.04
    Negative Logits
    omed
    -1.67
    κ
    -1.59
    ipl
    -1.51
    iple
    -1.49
    code
    -1.45
    ologies
    -1.44
    abases
    -1.42
    bi
    -1.42
    fig
    -1.40
    serial
    -1.40
    POSITIVE LOGITS
    enegger
    1.78
     Pledge
    1.60
     salute
    1.57
     enthusiastically
    1.56
     Geh
    1.47
    ersen
    1.46
     enjoys
    1.43
     passionately
    1.41
     yelled
    1.39
     wears
    1.38
    Act Density 0.039%

    No Known Activations