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

    Neuronpedia

    INDEX
    Explanations

    past tense forms of the verb "to be."

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

    frequently following "was"

    np_acts-logits-general · gemini-2.0-flash

    describing past states or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    current
    -0.58
     actuelles
    -0.58
    Current
    -0.56
     againſt
    -0.55
     fince
    -0.55
    ally
    -0.53
    なじ
    -0.53
    woordig
    -0.53
     current
    -0.52
     Chriftian
    -0.52
    POSITIVE LOGITS
     originally
    1.21
     originalmente
    0.99
     also
    0.98
     initially
    0.97
     previously
    0.97
     autrefois
    0.96
    originally
    0.91
     never
    0.87
     certainly
    0.87
     actually
    0.87
    Act Density 0.542%

    No Known Activations