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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing certainty or expectation

    oai_token-act-pair · gpt-3.5-turbo

    assertions of certainty or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     basically
    -0.85
     supposedly
    -0.84
     apparently
    -0.81
     essentially
    -0.80
     allegedly
    -0.73
    arently
    -0.73
     finally
    -0.73
     obviously
    -0.72
     purportedly
    -0.72
     presumably
    -0.70
    POSITIVE LOGITS
     underestimated
    0.72
    eds
    0.71
    racted
    0.69
    onen
    0.67
    gged
    0.66
    ciplinary
    0.64
     preferable
    0.64
    ented
    0.62
     underest
    0.62
    ounters
    0.62
    Act Density 0.324%

    No Known Activations