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

    Neuronpedia

    INDEX
    Explanations

    patterns related to energy amplification and its metrics in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    berger
    -0.17
    ube
    -0.15
    okt
    -0.15
    uber
    -0.15
    uzu
    -0.14
    iran
    -0.14
    aval
    -0.14
     Sir
    -0.14
    apur
    -0.14
    물
    -0.14
    POSITIVE LOGITS
    acea
    0.15
    /pop
    0.15
     Sapphire
    0.15
     خرد
    0.14
     té
    0.13
    Ńå·ŀ
    0.13
     sadd
    0.13
     neurop
    0.13
    æ°
    0.13
    -initial
    0.13
    Act Density 0.226%

    No Known Activations