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

    Neuronpedia

    INDEX
    Explanations

    the verb "was" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the verb "was" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbnails
    -0.68
     mentions
    -0.67
    workers
    -0.67
     âĶľ
    -0.64
    reports
    -0.61
     backdrop
    -0.60
     elabor
    -0.60
     summarizes
    -0.60
     dictates
    -0.60
     glances
    -0.59
    POSITIVE LOGITS
    nt
    0.96
    overe
    0.83
     somehow
    0.79
     gonna
    0.75
    piracy
    0.75
    omorphic
    0.74
     owed
    0.72
     worth
    0.70
     safe
    0.69
     indeed
    0.67
    Act Density 0.430%

    No Known Activations