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

    Neuronpedia

    INDEX
    Explanations

    verbs in the infinitive form

    oai_token-act-pair · gpt-3.5-turbo

    the verb "be" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rones
    -0.70
     Rab
    -0.70
     1922
    -0.63
     Blitz
    -0.63
     Kamp
    -0.63
     Rus
    -0.62
     Notting
    -0.61
     Kub
    -0.59
    ablishment
    -0.58
     Desire
    -0.58
    POSITIVE LOGITS
     likened
    0.97
     viewed
    0.96
     traced
    0.96
     seen
    0.95
    acons
    0.95
     easily
    0.92
     forgiven
    0.91
     construed
    0.90
     considered
    0.88
    leeve
    0.85
    Act Density 0.100%

    No Known Activations