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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "be" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    be followed by verb or adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.58
    typeorm
    -0.54
    ftagPool
    -0.53
     channels
    -0.50
    UnusedPrivate
    -0.49
     canais
    -0.48
    InteropServices
    -0.47
    IANGLES
    -0.46
     jurk
    -0.44
     hâte
    -0.43
    POSITIVE LOGITS
    getIs
    0.46
    BE
    0.44
    bé
    0.42
    Bé
    0.41
    Gle
    0.40
    Be
    0.40
    robin
    0.39
    Si
    0.39
    ponym
    0.38
    being
    0.38
    Act Density 0.043%

    No Known Activations