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

    Neuronpedia

    INDEX
    Explanations

    references to foundational or structural concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Freitas
    -0.50
    HttpGet
    -0.43
     CÓ
    -0.43
    SEX
    -0.42
     hottest
    -0.41
    Dakota
    -0.41
    nesota
    -0.40
    Sex
    -0.40
    Magick
    -0.40
     mex
    -0.39
    POSITIVE LOGITS
     Pillar
    1.33
     pillar
    1.30
     pillars
    1.19
     Pillars
    1.13
    pillar
    1.05
    pillars
    0.98
     PILL
    0.84
     pilares
    0.80
     pilar
    0.79
    illar
    0.77
    Act Density 0.012%

    No Known Activations