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

    Neuronpedia

    INDEX
    Explanations

    capital letters within text

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to credit and social development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aday
    -0.63
    tarian
    -0.61
    etsk
    -0.60
     pretext
    -0.60
    gio
    -0.60
    baugh
    -0.58
    taboola
    -0.58
    onomous
    -0.56
    gebra
    -0.56
    san
    -0.56
    POSITIVE LOGITS
    ILL
    1.18
    OUN
    1.17
     EDITION
    1.17
    IZ
    1.16
    IVES
    1.11
    OWN
    1.10
    EST
    1.10
     INV
    1.09
    ANG
    1.09
    ARE
    1.08
    Act Density 0.199%

    No Known Activations