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

    Neuronpedia

    INDEX
    Explanations

    questions and discussions surrounding societal issues and philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.02
    3:0.09
    4:0.48
    5:0.04
    6:0.03
    7:0.02
    8:0.05
    9:0.11
    10:0.01
    11:0.02
    Negative Logits
    ���
    -2.63
    ouble
    -2.29
    ilan
    -2.17
    iHUD
    -2.12
    aples
    -2.10
    inery
    -1.93
    mone
    -1.89
    cffff
    -1.88
    udicrous
    -1.86
    aternity
    -1.85
    POSITIVE LOGITS
    ?
    5.17
    ?:
    4.99
    ?)
    4.71
    ?),
    4.66
    ?]
    4.64
    ?).
    4.55
    ?,
    4.39
    ?"
    4.22
    !?
    4.21
    ?!
    4.18
    Act Density 0.372%

    No Known Activations