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

    Neuronpedia

    INDEX
    Explanations

    terms related to security and compliance

    oai_token-act-pair · gpt-3.5-turbo

    topics related to compliance and regulatory concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rodham
    -0.58
    ursday
    -0.55
    review
    -0.52
     tweeted
    -0.52
     congratulations
    -0.52
     Newsp
    -0.51
    iversary
    -0.50
    NPR
    -0.50
     reprinted
    -0.50
     Hogan
    -0.50
    POSITIVE LOGITS
    )).
    0.77
     attRot
    0.73
    '.
    0.72
    )."
    0.71
    !).
    0.70
    !".
    0.68
    '."
    0.67
    ".
    0.66
    ]."
    0.66
     accordingly
    0.65
    Act Density 1.514%

    No Known Activations