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

    Neuronpedia

    INDEX
    Explanations

    abstract and vague references to concepts, often questioning clarity or certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.16
    3:0.07
    4:0.02
    5:0.04
    6:0.05
    7:0.16
    8:0.25
    9:0.03
    10:0.07
    11:0.04
    Negative Logits
     Kul
    -0.95
     Krug
    -0.92
     Das
    -0.92
    etheus
    -0.90
     Zer
    -0.90
     Ur
    -0.84
    uzzle
    -0.82
     Jag
    -0.81
    eeds
    -0.80
     Erie
    -0.80
    POSITIVE LOGITS
    ONSORED
    1.14
    VERTISEMENT
    0.92
     meets
    0.92
    Applic
    0.91
     disapp
    0.87
    disabled
    0.87
     <-
    0.87
    Parser
    0.85
    Exception
    0.85
    PLIED
    0.84
    Act Density 0.187%

    No Known Activations