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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and similar forms, indicating actions or occurrences in the context of events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holder
    -0.68
    erential
    -0.67
     slots
    -0.64
    holders
    -0.63
     expires
    -0.62
     newsletters
    -0.61
    keeping
    -0.61
    wealth
    -0.61
     Cosponsors
    -0.60
     Preferences
    -0.60
    POSITIVE LOGITS
     perpetrated
    1.28
     attributed
    1.08
     blamed
    1.07
     preceded
    1.06
     prosecuted
    1.05
     investigated
    1.04
     filmed
    1.03
     aven
    1.02
     prevented
    1.01
     witnessed
    1.01
    Act Density 0.204%

    No Known Activations