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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and political statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.89
    ecided
    -0.79
     toget
    -0.75
    nesday
    -0.75
     Anyway
    -0.74
    town
    -0.74
    yy
    -0.73
    ahime
    -0.71
    pload
    -0.71
    aran
    -0.70
    POSITIVE LOGITS
     slightest
    1.41
     illusion
    1.15
     presumption
    1.15
     whims
    1.14
     possibility
    1.09
     notion
    1.07
     assumption
    1.07
     greatest
    1.06
     same
    1.06
     perverse
    1.04
    Act Density 0.245%

    No Known Activations