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

    Neuronpedia

    INDEX
    Explanations

    mentions of warnings or cautionary statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "warning" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    animate
    -0.73
    anova
    -0.72
    hedral
    -0.69
    ophon
    -0.66
    morph
    -0.65
    inion
    -0.65
    ional
    -0.65
    uate
    -0.65
    growth
    -0.64
    ablished
    -0.64
    POSITIVE LOGITS
     Signs
    1.04
    warning
    1.03
     signs
    0.96
     warnings
    0.90
     warning
    0.88
    warn
    0.84
     Warn
    0.84
     Warning
    0.83
     disclaimer
    0.81
    tale
    0.77
    Act Density 0.035%

    No Known Activations