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

    Neuronpedia

    INDEX
    Explanations

    expressions that denote exclusivity or singularity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.08
    3:0.09
    4:0.08
    5:0.07
    6:0.06
    7:0.09
    8:0.09
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
     ECB
    -2.75
    uador
    -2.61
     Amend
    -2.42
    ��
    -2.40
     Constantine
    -2.36
     convol
    -2.33
     Schwartz
    -2.31
     pope
    -2.25
    enberg
    -2.23
     Palest
    -2.18
    POSITIVE LOGITS
    umerable
    2.29
    pedia
    2.26
     duplication
    2.24
    ilities
    2.23
    ility
    2.18
    ultimate
    2.12
    erous
    2.12
    orph
    2.11
     disliked
    2.10
     Minion
    2.10
    Act Density 0.000%

    No Known Activations