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

    Neuronpedia

    INDEX
    Explanations

    years and numbers in the past

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ological
    -0.71
    enary
    -0.64
    allows
    -0.64
    obic
    -0.63
    objects
    -0.63
    loop
    -0.62
    container
    -0.62
    wake
    -0.61
    %)
    -0.61
    continue
    -0.60
    POSITIVE LOGITS
     raining
    1.06
     obvious
    0.90
     inevitable
    0.89
     unclear
    0.87
     rumored
    0.80
     awhile
    0.80
     clear
    0.80
     hoped
    0.80
     evident
    0.79
     supposed
    0.78
    Act Density 0.117%

    No Known Activations