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

    Neuronpedia

    INDEX
    Explanations

    instances of verbs related to action or performance

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coup
    -0.73
     Recall
    -0.71
    iannopoulos
    -0.71
    ESE
    -0.68
     Few
    -0.68
    âĦ¢:
    -0.67
    ils
    -0.67
     Scroll
    -0.67
    xus
    -0.66
     Contains
    -0.66
    POSITIVE LOGITS
     gonna
    1.61
     going
    1.20
     trying
    1.16
     saying
    1.15
     talking
    1.12
     doing
    1.11
     kind
    1.09
     really
    1.07
     basically
    1.07
     afraid
    1.05
    Act Density 0.347%

    No Known Activations