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

    Neuronpedia

    INDEX
    Explanations

    references to small or low characteristics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umab
    -0.55
    uesas
    -0.50
    mployment
    -0.49
    pidou
    -0.48
     colesterol
    -0.47
    -0.45
    closedir
    -0.45
    iasis
    -0.45
    ango
    -0.45
    textAlignment
    -0.45
    POSITIVE LOGITS
     small
    1.35
    small
    1.27
     SMALL
    1.26
    Small
    1.23
     Small
    1.20
     tiny
    1.18
    SMALL
    1.15
     smaller
    1.02
     کوچک
    1.02
     smal
    1.00
    Act Density 0.861%

    No Known Activations