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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an extreme or critical situation

    oai_token-act-pair · gpt-3.5-turbo

    references to extreme levels or thresholds of various situations or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DRAG
    -0.71
     Ging
    -0.64
     Deal
    -0.58
     "$:/
    -0.57
     Spend
    -0.55
     Drag
    -0.53
     filler
    -0.53
     Surviv
    -0.53
     Span
    -0.53
     Grant
    -0.52
    POSITIVE LOGITS
     extent
    1.07
     detriment
    0.93
     fullest
    0.76
    venge
    0.72
     tune
    0.72
     approximation
    0.72
     podium
    0.71
     lengths
    0.70
     brink
    0.70
     extremes
    0.69
    Act Density 0.240%

    No Known Activations