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

    Neuronpedia

    INDEX
    Explanations

    URLs or website links

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pse
    -0.76
    umably
    -0.76
    lier
    -0.76
     anyway
    -0.72
     presumably
    -0.69
     worse
    -0.68
     epist
    -0.68
     metaph
    -0.67
    odox
    -0.66
    ols
    -0.64
    POSITIVE LOGITS
     Featuring
    1.55
     Whether
    1.41
     Includes
    1.30
     Learn
    1.30
     Each
    1.29
     Explore
    1.27
     Located
    1.23
     Designed
    1.22
     Additionally
    1.21
     Choose
    1.21
    Act Density 0.345%

    No Known Activations