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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the quality of a job or task being done

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing positive evaluations of performance or quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦
    -0.61
     fears
    -0.60
     Heard
    -0.60
     defeated
    -0.59
    raltar
    -0.58
     vanquished
    -0.58
    being
    -0.56
     defended
    -0.56
     occupied
    -0.56
     arsen
    -0.56
    POSITIVE LOGITS
     thing
    0.98
     job
    0.93
     deed
    0.85
     laundry
    0.84
     darn
    0.84
     homework
    0.84
     stint
    0.77
     AMA
    0.77
     chores
    0.76
     internship
    0.75
    Act Density 0.166%

    No Known Activations