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

    Neuronpedia

    INDEX
    Explanations

    instances of people expressing their opinions or providing input

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "weigh in" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\\\\\\\
    -0.80
    >>>>>>>>
    -0.77
    İĭ
    -0.72
     Lost
    -0.71
     Wonderland
    -0.70
    bys
    -0.70
    href
    -0.68
    iHUD
    -0.66
    shire
    -0.64
    nces
    -0.64
    POSITIVE LOGITS
     heaviest
    0.84
     volumes
    0.80
     weighing
    0.80
     shoulders
    0.76
     pros
    0.75
     weights
    0.74
     weigh
    0.74
     fists
    0.70
     weighs
    0.70
     loads
    0.67
    Act Density 0.113%

    No Known Activations