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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sphinx
    -0.15
    onn
    -0.15
     поÑħ
    -0.14
     Tat
    -0.14
    Ñĥва
    -0.14
     Bou
    -0.13
    ÅĻe
    -0.13
     seems
    -0.13
     promin
    -0.13
    ekt
    -0.13
    POSITIVE LOGITS
    -pro
    0.36
     most
    0.35
     PRO
    0.30
    PRO
    0.28
    most
    0.28
     Most
    0.27
    MOST
    0.27
    pro
    0.27
    Most
    0.27
     MOST
    0.25
    Act Density 0.028%

    No Known Activations