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

    Neuronpedia

    INDEX
    Explanations

    instances of the English language and its related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.31
    4:0.02
    5:0.02
    6:0.16
    7:0.08
    8:0.03
    9:0.08
    10:0.06
    11:0.08
    Negative Logits
     裏�
    -1.30
    xious
    -1.28
    cohol
    -1.28
    scl
    -1.27
    Downloadha
    -1.23
     toxins
    -1.22
    keyes
    -1.18
     nerv
    -1.16
     chemotherapy
    -1.16
    icides
    -1.15
    POSITIVE LOGITS
    enment
    1.33
     Sorcerer
    1.18
     Duel
    1.17
     Norn
    1.14
     Pole
    1.12
    enhagen
    1.12
     Mines
    1.11
    rue
    1.09
     Lobby
    1.09
     Cinema
    1.09
    Act Density 0.008%

    No Known Activations