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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing extreme or superlative characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to extremes or notable characteristics of people or things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    along
    -0.77
    Que
    -0.67
     Hes
    -0.67
     Qt
    -0.64
    folio
    -0.64
    ————
    -0.62
     Kub
    -0.62
    ogie
    -0.60
    Connector
    -0.60
    ¯¯¯¯
    -0.60
    POSITIVE LOGITS
     slightest
    0.94
     watered
    0.73
     ones
    0.69
     smallest
    0.69
     semblance
    0.69
    othes
    0.67
    itable
    0.67
     curs
    0.66
    uyomi
    0.65
     nodd
    0.65
    Act Density 0.289%

    No Known Activations