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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to scientific or technical definitions and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oca
    -0.18
    lobals
    -0.16
    icks
    -0.16
     Adler
    -0.15
    argout
    -0.15
    ικ
    -0.15
     LINEAR
    -0.14
    æĵ¦
    -0.14
    globals
    -0.14
    iversal
    -0.14
    POSITIVE LOGITS
     Ret
    0.17
    ret
    0.17
     Pro
    0.17
    fit
    0.17
    ann
    0.17
    -ret
    0.16
    avl
    0.16
    landa
    0.16
    Pro
    0.16
    awks
    0.15
    Act Density 0.036%

    No Known Activations