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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing emotions or states of being

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "great" or synonyms indicating positive feelings or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ward
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    ullah
    -0.64
     Ballard
    -0.63
    Fall
    -0.63
    ع
    -0.63
    vice
    -0.61
     Frankfurt
    -0.61
     Fall
    -0.59
     Ree
    -0.59
    POSITIVE LOGITS
    xual
    0.72
    ciating
    0.72
     suspense
    0.69
    hearted
    0.69
    faced
    0.68
    weet
    0.66
    selves
    0.66
    vier
    0.66
    ness
    0.66
     Tonight
    0.64
    Act Density 0.176%

    No Known Activations