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

    Neuronpedia

    INDEX
    Explanations

    questions or statements beginning with "Whether"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases starting with "whether."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OWN
    -0.65
     Pharma
    -0.65
     Downs
    -0.61
    ogie
    -0.60
    ursed
    -0.59
    washer
    -0.59
    rome
    -0.56
     Instructions
    -0.56
     Seeds
    -0.56
     Doors
    -0.56
    POSITIVE LOGITS
    theless
    1.02
    soever
    0.85
     Leilan
    0.71
    fy
    0.71
    icity
    0.64
     consciously
    0.63
    isSpecialOrderable
    0.61
     depends
    0.61
     intentional
    0.61
     depended
    0.58
    Act Density 0.020%

    No Known Activations