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

    Neuronpedia

    INDEX
    Explanations

    statements of certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    references to certainty and percentage-based assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.75
    isk
    -0.75
    isson
    -0.71
    pload
    -0.69
    zie
    -0.68
    ks
    -0.68
    worldly
    -0.67
     behav
    -0.67
    isc
    -0.66
    achus
    -0.66
    POSITIVE LOGITS
    heartedly
    0.83
     adhere
    0.71
    clear
    0.71
     agree
    0.70
     ethanol
    0.69
    reference
    0.68
     assured
    0.67
    inline
    0.65
    ascript
    0.65
    Authent
    0.65
    Act Density 0.036%

    No Known Activations