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

    Neuronpedia

    INDEX
    Explanations

    numerical data and references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Wunused
    -0.15
    SSI
    -0.15
     sint
    -0.14
    μÎŃ
    -0.14
     Τα
    -0.13
    SizePolicy
    -0.13
     onwards
    -0.13
     à¹Ģว
    -0.13
    udu
    -0.13
    PPP
    -0.12
    POSITIVE LOGITS
     Al
    0.22
     Ag
    0.22
     Ak
    0.22
     Ab
    0.22
     Ah
    0.22
     Alb
    0.20
     AK
    0.19
    Al
    0.19
    ÂłA
    0.19
     Ad
    0.19
    Act Density 0.190%

    No Known Activations