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

    Neuronpedia

    INDEX
    Explanations

    references to performances or events occurring on stage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ness
    -0.17
    aries
    -0.16
    sov
    -0.16
    tring
    -0.16
    rtle
    -0.16
    ngle
    -0.16
    lope
    -0.15
    rych
    -0.15
    ntag
    -0.15
    ude
    -0.15
    POSITIVE LOGITS
    coach
    0.45
    craft
    0.35
    hands
    0.23
    Presence
    0.22
    Craft
    0.21
     presence
    0.21
    hand
    0.21
     Presence
    0.20
     fright
    0.20
    /screen
    0.20
    Act Density 0.016%

    No Known Activations