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

    Neuronpedia

    INDEX
    Explanations

    various usages of the word 'thought'

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words that encapsulate the concept of thoughtfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -0.73
     Peninsula
    -0.71
    BIP
    -0.68
    ARDS
    -0.66
    anca
    -0.63
    arta
    -0.63
    ño
    -0.63
    opard
    -0.62
    ALL
    -0.62
    lain
    -0.61
    POSITIVE LOGITS
    fully
    1.37
    fulness
    1.31
    lessly
    1.23
     provoking
    1.15
    less
    0.98
    lessness
    0.97
    ful
    0.95
    crime
    0.87
    phis
    0.87
    istically
    0.81
    Act Density 0.041%

    No Known Activations