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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or future action

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "will."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    licted
    -0.66
     Measures
    -0.66
    eatured
    -0.65
     Theme
    -0.64
    hea
    -0.61
     Modified
    -0.60
    AMA
    -0.59
    ocular
    -0.58
     Eater
    -0.58
     Hits
    -0.57
    POSITIVE LOGITS
     gladly
    1.20
     be
    1.07
     surely
    0.99
     continue
    0.98
     undoubtedly
    0.96
     NEVER
    0.95
     inevitably
    0.90
     never
    0.90
     definitely
    0.89
     find
    0.88
    Act Density 0.197%

    No Known Activations