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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statements of fact or assertion

    oai_token-act-pair · gpt-3.5-turbo

    the verb "to be" in various forms indicating states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atives
    -0.70
    ossom
    -0.69
     Moines
    -0.67
    urry
    -0.67
    onnaissance
    -0.66
     mentions
    -0.65
    llor
    -0.64
    enture
    -0.64
    udeau
    -0.63
     margin
    -0.61
    POSITIVE LOGITS
     indeed
    1.13
    nt
    1.01
     not
    0.96
     unlikely
    0.95
     owed
    0.94
     somehow
    0.93
    rael
    0.91
     worth
    0.88
     likely
    0.87
     destined
    0.86
    Act Density 0.450%

    No Known Activations