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

    Neuronpedia

    INDEX
    Explanations

    references to a specific variable or element denoted by 'r'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ponte
    -0.48
     gesta
    -0.42
    Capa
    -0.40
    ähne
    -0.40
     Eins
    -0.40
    mitos
    -0.40
    づ
    -0.40
    Composable
    -0.40
    ביוגרפיה
    -0.39
    渍
    -0.39
    POSITIVE LOGITS
     r
    3.09
    r
    1.75
    ｒ
    1.18
    𝑟
    1.05
     rr
    1.04
     р
    0.93
     ر
    0.91
    getR
    0.91
    ร
    0.89
    𝐫
    0.89
    Act Density 0.192%

    No Known Activations