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

    Neuronpedia

    INDEX
    Explanations

    questions and reflections about values and beliefs in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -1.29
    :✨
    -1.16
     kaarangay
    -1.03
    Datuak
    -0.99
     myſelf
    -0.99
     purpoſe
    -0.99
    ſelves
    -0.96
     Majefty
    -0.96
     neceff
    -0.96
    EndGlobalSection
    -0.95
    POSITIVE LOGITS
     also
    1.04
     likewise
    0.70
    ...
    0.70
     even
    0.69
     that
    0.69
    also
    0.67
     aussi
    0.65
     Also
    0.65
     for
    0.62
    …
    0.62
    Act Density 0.421%

    No Known Activations