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

    Neuronpedia

    INDEX
    Explanations

    phrases related to formal statements or announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "was" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburg
    -0.83
     Quantity
    -0.78
    alus
    -0.74
     Spani
    -0.73
    know
    -0.71
    inav
    -0.68
    uld
    -0.66
    izons
    -0.65
    bury
    -0.64
    fields
    -0.64
    POSITIVE LOGITS
     unclear
    0.94
     also
    0.93
     widely
    0.91
     awarded
    0.90
     incon
    0.87
     unlikely
    0.86
     presented
    0.86
     billed
    0.86
     supposed
    0.85
     meant
    0.85
    Act Density 0.316%

    No Known Activations