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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "was" and its variations to indicate states or conditions

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

    "Was" followed by a past participle or adjective

    np_acts-logits-general · gemini-2.0-flash

    past states and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     actualidad
    -0.63
    currently
    -0.59
     Currently
    -0.59
     atualmente
    -0.56
    Currently
    -0.56
     currently
    -0.56
     actuellement
    -0.55
     attualmente
    -0.52
    rungsseite
    -0.52
     queſta
    -0.52
    POSITIVE LOGITS
     originally
    0.82
     previously
    0.72
     ursprünglich
    0.63
     originalmente
    0.60
    originally
    0.58
     formerly
    0.58
    wolves
    0.55
     initially
    0.55
     recently
    0.53
    previously
    0.52
    Act Density 0.580%

    No Known Activations