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

    Neuronpedia

    INDEX
    Explanations

    phrases related to warnings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "warning."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    animate
    -0.77
    ophon
    -0.72
    hedral
    -0.72
    inion
    -0.72
    anova
    -0.71
    atism
    -0.70
    gres
    -0.69
    morph
    -0.69
    tiny
    -0.67
    artney
    -0.65
    POSITIVE LOGITS
    warning
    1.00
     Signs
    0.97
     warnings
    0.92
     warning
    0.90
     Warning
    0.89
     signs
    0.89
     Warn
    0.84
     disclaimer
    0.83
    warn
    0.80
    llor
    0.76
    Act Density 0.033%

    No Known Activations