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

    Neuronpedia

    INDEX
    Explanations

    past participle verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating past actions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izable
    -0.69
    now
    -0.63
    IVE
    -0.63
    Must
    -0.63
    buquerque
    -0.61
     now
    -0.61
    Not
    -0.61
    ierrez
    -0.60
     Not
    -0.60
    today
    -0.60
    POSITIVE LOGITS
     misled
    1.00
     tricked
    0.97
     WARN
    0.96
     briefed
    0.95
     spared
    0.92
     warned
    0.92
     robbed
    0.91
     deceived
    0.91
     hijacked
    0.89
     expelled
    0.89
    Act Density 0.102%

    No Known Activations