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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-importance or confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ainless
    -0.14
    ilog
    -0.14
    _RENDERER
    -0.14
    itus
    -0.14
     nÃło
    -0.13
    дов
    -0.13
    .www
    -0.13
    phinx
    -0.13
    universal
    -0.13
     existence
    -0.13
    POSITIVE LOGITS
     possibilities
    0.19
     activity
    0.18
     Activity
    0.17
     promise
    0.16
    osu
    0.15
     possibility
    0.15
     symbolism
    0.15
    Activity
    0.15
     detail
    0.15
     surprises
    0.15
    Act Density 0.072%

    No Known Activations