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

    Neuronpedia

    INDEX
    Explanations

    future intentions or plans mentioned in a negative light

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating improbability or denial of occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guessing
    -0.69
    OTO
    -0.68
     refusing
    -0.67
    cule
    -0.67
     pledging
    -0.66
     likened
    -0.65
     withholding
    -0.65
     vowed
    -0.65
     gazing
    -0.64
    Reviewer
    -0.64
    POSITIVE LOGITS
     exist
    1.37
     suffice
    1.34
     occur
    1.34
     affect
    1.31
     resonate
    1.25
     happen
    1.24
     succeed
    1.24
     survive
    1.14
    exist
    1.12
     translate
    1.10
    Act Density 0.265%

    No Known Activations