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

    Neuronpedia

    INDEX
    Explanations

    words related to evaluation, criticism, or assessment with emphasis on certainty or intensity

    oai_token-act-pair · gpt-3.5-turbo

    phrases suggesting legality or regulatory status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icism
    -0.74
    alion
    -0.68
    culosis
    -0.68
    dress
    -0.64
    ortmund
    -0.62
    atche
    -0.62
    APTER
    -0.62
    cation
    -0.61
    DOS
    -0.59
    éĹ
    -0.58
    POSITIVE LOGITS
     interchangeable
    0.86
    abouts
    0.74
    types
    0.70
     extensions
    0.70
     themselves
    0.69
     jelly
    0.69
     alike
    0.69
    rely
    0.67
     indications
    0.67
     unanimous
    0.67
    Act Density 0.528%

    No Known Activations