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

    Neuronpedia

    INDEX
    Explanations

    information related to official statements or press releases

    oai_token-act-pair · gpt-3.5-turbo

    statements of intent or actions related to monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     regenerate
    -0.74
     unstoppable
    -0.73
     telesc
    -0.71
     regener
    -0.71
     endeav
    -0.70
     skelet
    -0.69
     hero
    -0.69
     axe
    -0.68
     domestically
    -0.68
     knockout
    -0.67
    POSITIVE LOGITS
    About
    1.37
    Meanwhile
    1.36
    Asked
    1.35
    According
    1.33
    Newsletter
    1.28
    Another
    1.27
    Contribut
    1.27
    Instead
    1.27
    However
    1.27
    Related
    1.26
    Act Density 0.624%

    No Known Activations