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

    form of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.76
     Highlights
    -0.69
    brate
    -0.68
    enary
    -0.66
     Visit
    -0.63
    soever
    -0.61
     Supports
    -0.61
    ãĤ©
    -0.61
     Adds
    -0.61
     Horizons
    -0.59
    POSITIVE LOGITS
    wolves
    1.01
     already
    1.00
     eventually
    0.99
     evidently
    0.98
     slipping
    0.97
    nt
    0.97
     indeed
    0.96
    hes
    0.95
     never
    0.95
     becoming
    0.94
    Act Density 0.301%

    No Known Activations