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

    Neuronpedia

    INDEX
    Explanations

    references to spiritual or religious entities and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.15
    3:0.12
    4:0.18
    5:0.03
    6:0.05
    7:0.16
    8:0.04
    9:0.03
    10:0.06
    11:0.10
    Negative Logits
    escription
    -1.89
     elim
    -1.67
    ensibly
    -1.55
    uphem
    -1.38
    antically
    -1.37
    itory
    -1.33
    occup
    -1.32
    igated
    -1.30
    phasis
    -1.28
    esm
    -1.28
    POSITIVE LOGITS
     ;)
    1.44
    !]
    1.28
     🙂
    1.28
    stadt
    1.27
     )]
    1.26
     ));
    1.26
    �
    1.26
    BTC
    1.23
     ))
    1.23
    …)
    1.22
    Act Density 0.003%

    No Known Activations