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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the use of creative assets and their arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.11
    2:0.03
    3:0.02
    4:0.02
    5:0.03
    6:0.27
    7:0.09
    8:0.12
    9:0.13
    10:0.03
    11:0.02
    Negative Logits
    Berry
    -3.37
     Mystic
    -3.34
     Lynn
    -3.31
     FM
    -3.24
     insomnia
    -3.21
     salmon
    -3.20
     spirituality
    -3.17
     monastery
    -3.16
     Donovan
    -3.15
     lighthouse
    -3.13
    POSITIVE LOGITS
     Sketch
    4.97
    Ã
    3.46
     Costume
    3.31
     guiIcon
    3.21
    Spr
    3.18
    Shape
    3.13
    enegger
    3.10
     Canaver
    3.07
    obj
    3.06
     Sty
    3.01
    Act Density 0.000%

    No Known Activations