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

    Neuronpedia

    INDEX
    Explanations

    percentage values and statistical comparisons

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Wicidata
    -0.64
    NUMX
    -0.60
    randrange
    -0.59
     kasarigan
    -0.57
    APOLIS
    -0.55
    AndEndTag
    -0.53
     of
    -0.52
     useStyles
    -0.50
    Jîn
    -0.50
    hyrchwyd
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    0.65
    IndentedString
    0.65
     Беларусь
    0.54
    awtextra
    0.51
     hombros
    0.50
    tamol
    0.49
     épaules
    0.49
     Ponta
    0.49
    ConstraintMaker
    0.48
     Regime
    0.48
    Act Density 0.065%

    No Known Activations