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

    Neuronpedia

    INDEX
    Explanations

    phrases that negate or contradict statements

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and auxiliary verbs that indicate conditionality or connection between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HEAD
    -0.67
     Tid
    -0.59
     champ
    -0.57
     Matrix
    -0.57
     Stockholm
    -0.54
    figure
    -0.54
     ven
    -0.53
    piring
    -0.53
    Ax
    -0.52
     bearer
    -0.52
    POSITIVE LOGITS
     nor
    1.54
     consequently
    1.28
     therefore
    1.22
     neither
    1.20
     furthermore
    1.17
     Nor
    1.16
     moreover
    1.11
     hence
    1.07
    nor
    1.04
     thus
    1.01
    Act Density 0.352%

    No Known Activations