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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.74
     Италијани
    -0.68
    хьтан
    -0.63
     '\\;'
    -0.62
    addCriterion
    -0.61
    IntoConstraints
    -0.61
     ویکی‌پدی
    -0.59
    GOTREF
    -0.58
     <<<<<<<<<<<<<<
    -0.57
     Biôgrafia
    -0.57
    POSITIVE LOGITS
     pretty
    0.49
     only
    0.46
     a
    0.45
     also
    0.45
     is
    0.44
     tää
    0.44
     It
    0.44
     almost
    0.43
     certainly
    0.43
     very
    0.41
    Act Density 0.440%

    No Known Activations