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

    Neuronpedia

    INDEX
    Explanations

    phrases related to agreements or deals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate consent or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.87
    folios
    -0.73
    vantage
    -0.71
    crow
    -0.69
     earthqu
    -0.65
    quin
    -0.63
    undown
    -0.62
    inas
    -0.62
    oiler
    -0.62
    xon
    -0.60
    POSITIVE LOGITS
     to
    1.04
     unanimously
    0.99
     thereto
    0.96
     upon
    0.86
     indemn
    0.81
     beforehand
    0.79
     voluntarily
    0.76
    upon
    0.75
     terms
    0.73
     agreements
    0.71
    Act Density 0.032%

    No Known Activations