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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating determination or intention

    oai_token-act-pair · gpt-3.5-turbo

    contractions and forms of "to be," especially in negative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inav
    -0.80
    icle
    -0.66
    racuse
    -0.66
    udos
    -0.65
    odied
    -0.64
    icles
    -0.63
    ital
    -0.62
     pecul
    -0.61
    ciating
    -0.61
     resembles
    -0.60
    POSITIVE LOGITS
     gonna
    1.50
     willing
    1.41
     ready
    1.29
     going
    1.27
     prepared
    1.14
     sorry
    1.07
     obligated
    1.05
    ready
    1.01
     interested
    1.00
     afraid
    1.00
    Act Density 0.248%

    No Known Activations