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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ°ãģĭãĤĬ
    -0.19
    omu
    -0.15
     almost
    -0.15
    isu
    -0.14
     поÑĩÑĤи
    -0.14
     nearly
    -0.14
    Å¡ti
    -0.13
     Almost
    -0.13
    Almost
    -0.13
    _recent
    -0.13
    POSITIVE LOGITS
     maybe
    0.21
     perhaps
    0.21
     qualche
    0.18
    maybe
    0.18
    -нибÑĥдÑĮ
    0.17
    aybe
    0.17
    perhaps
    0.16
     possibly
    0.16
     something
    0.16
     tomorrow
    0.16
    Act Density 0.419%

    No Known Activations