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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inflation and exaggeration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inflated or exaggerated claims and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.98
    atche
    -0.80
    sf
    -0.74
    clerosis
    -0.71
    abiding
    -0.71
    sen
    -0.71
    arij
    -0.71
    abetes
    -0.70
    ittee
    -0.69
    avis
    -0.69
    POSITIVE LOGITS
     inflated
    1.14
     corrid
    0.92
     representations
    0.84
     caric
    0.82
     versions
    0.81
     exaggerated
    0.78
     expectations
    0.76
     explanations
    0.74
    ulated
    0.73
     proport
    0.73
    Act Density 0.018%

    No Known Activations