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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating strong certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vernment
    -0.89
    çĶ°
    -0.69
    çīĪ
    -0.68
    gdala
    -0.68
    intosh
    -0.67
    ufact
    -0.67
    èĢħ
    -0.66
    Export
    -0.64
    IDA
    -0.62
    INT
    -0.61
    POSITIVE LOGITS
    ties
    0.89
    fire
    0.86
    sk
    0.85
    footed
    0.83
    ty
    0.78
    faced
    0.74
     enough
    0.71
     tack
    0.71
     damn
    0.71
    ples
    0.70
    Act Density 0.019%

    No Known Activations