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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to textures

    oai_token-act-pair · gpt-3.5-turbo

    words with the suffix '-y' or '-ed'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    employ
    -0.75
    CVE
    -0.70
    REP
    -0.69
    esson
    -0.69
     Leilan
    -0.68
    MRI
    -0.67
    SEA
    -0.66
    podcast
    -0.66
    igun
    -0.66
    GV
    -0.63
    POSITIVE LOGITS
     equivalents
    0.78
     greens
    0.75
     substr
    0.75
     plains
    0.74
     beverage
    0.74
     slopes
    0.74
     tones
    0.73
     compounds
    0.73
     waters
    0.71
     beverages
    0.70
    Act Density 0.116%

    No Known Activations