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

    Neuronpedia

    INDEX
    Explanations

    general statements with the phrase "there are many"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the existence of numerous items or reasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ENCE
    -0.75
    slaught
    -0.74
    igation
    -0.74
    aeus
    -0.73
    athon
    -0.73
    inth
    -0.73
    isition
    -0.72
    culosis
    -0.72
    ãĥ¼ãĥ«
    -0.72
    iliation
    -0.72
    POSITIVE LOGITS
     reasons
    1.59
     ways
    1.53
     similarities
    1.29
     exceptions
    1.26
     caveats
    1.26
     examples
    1.23
     occasions
    1.22
     misconceptions
    1.20
     nuances
    1.15
     parallels
    1.15
    Act Density 0.176%

    No Known Activations