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

    Neuronpedia

    INDEX
    Explanations

    references to the reader or the concept of inclusivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.17
    3:0.07
    4:0.17
    5:0.04
    6:0.17
    7:0.09
    8:0.04
    9:0.04
    10:0.06
    11:0.08
    Negative Logits
    Ping
    -1.36
    cription
    -1.32
    Initialized
    -1.31
    istent
    -1.29
    claimed
    -1.28
     Checks
    -1.28
    Round
    -1.28
     Seaf
    -1.26
     Mahjong
    -1.26
    phony
    -1.26
    POSITIVE LOGITS
     attest
    1.63
     pse
    1.61
    guide
    1.54
    版
    1.50
    >:
    1.49
    asin
    1.48
     magnification
    1.47
    antage
    1.46
    bos
    1.46
     rooft
    1.38
    Act Density 0.000%

    No Known Activations