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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating being in a position of obligation or responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    under contract or obligation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PYX
    -0.46
     Ciencia
    -0.44
     pêche
    -0.43
    Relevance
    -0.40
    後來
    -0.40
    URLException
    -0.40
    твра
    -0.39
     Educación
    -0.39
    survival
    -0.39
    后来
    -0.38
    POSITIVE LOGITS
     under
    0.79
    under
    0.61
    Under
    0.59
     Under
    0.57
     UNDER
    0.57
     undergoes
    0.55
     undergoing
    0.55
     wikipagina
    0.49
    UNDER
    0.49
    受到了
    0.47
    Act Density 0.016%

    No Known Activations