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

    Neuronpedia

    INDEX
    Explanations

    instances where someone does a good, outstanding, or great job

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assess the quality or effectiveness of actions or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arri
    -0.71
     fears
    -0.69
     Cursed
    -0.68
     Courage
    -0.67
    went
    -0.65
    FontSize
    -0.65
     Made
    -0.64
     Returning
    -0.64
     Torn
    -0.63
     Heard
    -0.63
    POSITIVE LOGITS
     homework
    0.86
     grunt
    0.86
     thing
    0.80
     job
    0.77
     justice
    0.76
     laundry
    0.74
     deed
    0.74
    judicial
    0.72
     chores
    0.71
     darn
    0.68
    Act Density 0.119%

    No Known Activations