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

    Neuronpedia

    INDEX
    Explanations

    past and present forms of the verb "to be"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wick
    -0.17
    æĬŀ
    -0.16
    ?q
    -0.16
    rech
    -0.15
    ullo
    -0.15
    tright
    -0.15
    leck
    -0.15
    ague
    -0.15
    rene
    -0.14
    าม
    -0.14
    POSITIVE LOGITS
    ÑĥÑĢг
    0.15
    0.14
    ìĭł
    0.14
     nor
    0.14
    ledo
    0.14
     "
    0.14
    udi
    0.13
     neither
    0.13
    _decorator
    0.13
    ovit
    0.13
    Act Density 0.073%

    No Known Activations