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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" in various conjugations and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĩº
    -0.15
    enger
    -0.15
    æIJ
    -0.15
    ulia
    -0.14
    ARIANT
    -0.14
    /loose
    -0.13
    pler
    -0.13
    )[:
    -0.13
    oker
    -0.13
     æ©
    -0.13
    POSITIVE LOGITS
     stato
    0.24
     stati
    0.23
     become
    0.23
     gone
    0.21
     gaan
    0.21
     arriv
    0.21
     stata
    0.21
     state
    0.20
    Been
    0.18
     Become
    0.17
    Act Density 0.034%

    No Known Activations