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

    Neuronpedia

    INDEX
    Explanations

    passive voice statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and related verb forms indicating past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     adjustment
    -0.66
     correction
    -0.66
    inner
    -0.66
     evolves
    -0.65
     goodbye
    -0.63
     entails
    -0.62
     Needs
    -0.61
     sexes
    -0.61
     stripe
    -0.60
     emphasis
    -0.60
    POSITIVE LOGITS
     assassinated
    0.87
    icz
    0.82
    uala
    0.82
    senal
    0.81
     reportedly
    0.78
     congratulated
    0.77
    ŃĶ
    0.77
     likewise
    0.76
     accused
    0.76
     sentenced
    0.75
    Act Density 0.374%

    No Known Activations