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

    Neuronpedia

    INDEX
    Explanations

    concepts related to law, morality, and the soul

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    رÙĪب
    -0.15
    jspx
    -0.14
    -nil
    -0.14
    shint
    -0.14
    orama
    -0.14
    λμ
    -0.14
     sooner
    -0.14
    llen
    -0.14
    Muon
    -0.14
    tright
    -0.14
    POSITIVE LOGITS
     Aqu
    0.19
     beat
    0.19
     appet
    0.18
     Appet
    0.17
     corrupt
    0.16
     appetite
    0.16
     speculative
    0.15
    irl
    0.15
     infused
    0.15
     passions
    0.15
    Act Density 0.043%

    No Known Activations