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

    Neuronpedia

    INDEX
    Explanations

    statistical phrases related to probabilities and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bernstein
    -0.15
    -lfs
    -0.15
    odox
    -0.14
    cki
    -0.14
     Bread
    -0.14
     lap
    -0.14
     laps
    -0.14
    croft
    -0.14
     Lis
    -0.13
    asm
    -0.13
    POSITIVE LOGITS
    IRR
    0.16
    ëį
    0.16
    enn
    0.15
    regon
    0.15
    nat
    0.15
     γεÏģ
    0.14
    nr
    0.14
     Tüm
    0.14
    an
    0.14
    allen
    0.14
    Act Density 0.072%

    No Known Activations