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

    Neuronpedia

    INDEX
    Explanations

    words related to certainty or high likelihood

    oai_token-act-pair · gpt-3.5-turbo

    the word "certainly" indicating affirmation or certainty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Offline
    -0.69
     respectively
    -0.69
    bowl
    -0.66
    INT
    -0.62
    ulative
    -0.62
    common
    -0.61
    lay
    -0.61
    ollen
    -0.61
     Power
    -0.60
    pocket
    -0.60
    POSITIVE LOGITS
    tsy
    0.77
    mond
    0.74
     Trident
    0.71
     detract
    0.71
    entimes
    0.70
     certainly
    0.70
     qualifies
    0.69
     merits
    0.68
    olkien
    0.67
    Certainly
    0.66
    Act Density 0.014%

    No Known Activations