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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and parameters in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inverse
    -0.15
    esh
    -0.15
     Seamless
    -0.15
    ucid
    -0.15
    inverse
    -0.14
     Honest
    -0.14
     principal
    -0.14
    ILA
    -0.14
    ishi
    -0.13
    kest
    -0.13
    POSITIVE LOGITS
    CG
    0.21
     CG
    0.21
    cg
    0.20
    CGRect
    0.19
    .CG
    0.18
    (CG
    0.17
     cg
    0.16
    FLT
    0.16
    	CG
    0.16
     rect
    0.16
    Act Density 0.004%

    No Known Activations