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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "ar"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esc
    -0.22
    ersen
    -0.19
    enko
    -0.16
    arten
    -0.15
    iques
    -0.15
    ogs
    -0.15
     Gut
    -0.15
    arte
    -0.15
    ends
    -0.15
    empor
    -0.14
    POSITIVE LOGITS
    rows
    0.22
    ithmetic
    0.20
    ched
    0.19
    hythm
    0.19
    uments
    0.18
     Ar
    0.18
    beiter
    0.17
    angement
    0.17
    beiten
    0.17
    Ïģαβ
    0.17
    Act Density 0.046%

    No Known Activations