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

    Neuronpedia

    INDEX
    Explanations

    grammatical forms and morphological variations of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rieb
    -0.17
     @$_
    -0.17
    âĻ¡
    -0.15
    ÑĢиÑģÑĤи
    -0.14
    .bootstrap
    -0.14
    ÅĻÃŃd
    -0.14
    bersome
    -0.14
    _Tab
    -0.14
    è·
    -0.13
    ä»ģ
    -0.13
    POSITIVE LOGITS
     Gr
    0.27
     gr
    0.26
    gr
    0.22
    Gr
    0.21
    .Gr
    0.20
    elda
    0.20
    (gr
    0.20
     GR
    0.18
    wald
    0.18
    /gr
    0.17
    Act Density 0.029%

    No Known Activations