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

    Neuronpedia

    INDEX
    Explanations

    superlatives, especially those relating to extremes like "est" or "iest"

    oai_token-act-pair · gpt-3.5-turbo

    superlative forms of adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    krit
    -0.78
    æ©
    -0.74
    isson
    -0.73
    ilater
    -0.72
    mbuds
    -0.70
    dinand
    -0.69
    bara
    -0.69
    mberg
    -0.66
    sem
    -0.65
    vim
    -0.65
    POSITIVE LOGITS
     imaginable
    1.08
     conceivable
    0.97
     possible
    0.92
     practicable
    0.78
     thing
    0.77
    anding
    0.75
     sounding
    0.73
    ream
    0.71
     ever
    0.71
    ness
    0.69
    Act Density 0.023%

    No Known Activations