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

    Neuronpedia

    INDEX
    Explanations

    references to ownership and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.02
    2:0.07
    3:0.15
    4:0.25
    5:0.04
    6:0.04
    7:0.05
    8:0.06
    9:0.06
    10:0.05
    11:0.07
    Negative Logits
    advertisement
    -1.70
     Frie
    -1.48
    .)
    -1.42
     Slug
    -1.42
    glers
    -1.42
     Luk
    -1.40
     Canaver
    -1.39
    phabet
    -1.38
    depending
    -1.34
     apiece
    -1.34
    POSITIVE LOGITS
    intend
    1.78
    アル
    1.43
    ught
    1.41
    gans
    1.40
     faire
    1.36
     ever
    1.32
    igne
    1.27
     dare
    1.26
     hesitate
    1.25
     justice
    1.25
    Act Density 0.026%

    No Known Activations