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

    Neuronpedia

    INDEX
    Explanations

    references to a conceptual framework or systematic analysis involving "black box" functions in computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.19
    2:0.06
    3:0.05
    4:0.05
    5:0.02
    6:0.10
    7:0.11
    8:0.02
    9:0.05
    10:0.07
    11:0.10
    Negative Logits
    horn
    -2.68
     Jarvis
    -2.63
     tracker
    -2.55
     Petra
    -2.53
    trace
    -2.48
    Champ
    -2.44
     Icar
    -2.38
     Jasper
    -2.35
     Vance
    -2.35
     jackets
    -2.34
    POSITIVE LOGITS
     multiply
    4.57
     multiplication
    4.56
     multiplying
    4.19
     multipl
    4.18
     multiplied
    3.88
    multipl
    3.57
    Mult
    3.56
     Multi
    3.04
     divide
    2.97
     multiplier
    2.91
    Act Density 0.001%

    No Known Activations