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

    Neuronpedia

    INDEX
    Explanations

    various forms of the verb "to be" and their different tenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.63
     itong
    -0.63
     المعيارى
    -0.63
     Houſe
    -0.60
     neuve
    -0.60
    verwijspagina
    -0.60
    IVEREF
    -0.59
     Italijani
    -0.58
     vectorielles
    -0.57
    ěstí
    -0.57
    POSITIVE LOGITS
     a
    0.67
     an
    0.61
     Director
    0.56
     often
    0.55
     part
    0.55
     involved
    0.54
     the
    0.53
     instrumental
    0.52
     frequently
    0.51
     active
    0.51
    Act Density 0.203%

    No Known Activations