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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral and ethical philosophy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     partly
    -0.15
     gets
    -0.14
    æĬĬ
    -0.13
    uses
    -0.13
     using
    -0.13
     people
    -0.13
     uses
    -0.13
     clos
    -0.13
     lots
    -0.13
     à¹Ĩ
    -0.13
    POSITIVE LOGITS
    sans
    0.16
    ãģ«ãģ¦
    0.16
    upon
    0.15
    é¡»
    0.14
    viz
    0.14
    _via
    0.13
    ~-~-~-~-
    0.13
     OTHERWISE
    0.13
     prez
    0.13
    pst
    0.13
    Act Density 3.698%

    No Known Activations