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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotions and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    est
    -0.20
    imar
    -0.15
    Ľå»º
    -0.15
    á»ĥn
    -0.15
    avier
    -0.14
    lon
    -0.14
    ãĥ¬ãĤ¤
    -0.14
    ST
    -0.14
    <-
    -0.13
    اÙģ
    -0.13
    POSITIVE LOGITS
     most
    0.38
     MOST
    0.30
    most
    0.28
    Most
    0.27
     Most
    0.27
    _most
    0.26
    MOST
    0.25
    æľĢ
    0.22
     सबस
    0.21
     ê°Ģìŀ¥
    0.20
    Act Density 0.066%

    No Known Activations