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

    Neuronpedia

    INDEX
    Explanations

    the word "null" or related terms, suggesting a focus on null values or invalidating actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nullification or invalidation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     exha
    -0.82
     millenn
    -0.81
    Downloadha
    -0.79
     livest
    -0.77
    BOOK
    -0.77
     ingred
    -0.74
     toget
    -0.74
    DonaldTrump
    -0.71
    ilitating
    -0.68
    ħĭ
    -0.67
    POSITIVE LOGITS
    ifying
    1.21
    ified
    1.20
    ptr
    1.19
    ifies
    1.16
    ification
    1.12
    ities
    1.05
    ify
    1.01
    ifier
    0.97
    eenth
    0.96
    ity
    0.95
    Act Density 0.018%

    No Known Activations