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

    Neuronpedia

    INDEX
    Explanations

    the phrase "all in all."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize totality or completeness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    namese
    -0.72
    lash
    -0.72
    anova
    -0.72
    rists
    -0.69
    lav
    -0.69
    illac
    -0.69
    tis
    -0.69
    yip
    -0.68
    nect
    -0.67
    idable
    -0.67
    POSITIVE LOGITS
     manner
    1.10
    ocating
    1.03
     sorts
    0.86
     kinds
    0.86
    uding
    0.83
    igator
    0.80
    igators
    0.78
    iance
    0.76
    ogene
    0.75
    usion
    0.75
    Act Density 0.042%

    No Known Activations