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

    Neuronpedia

    INDEX
    Explanations

    specific sections or parts of a document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cia
    -0.69
    ILLE
    -0.67
     monetary
    -0.66
     opio
    -0.66
    gerald
    -0.64
    natureconservancy
    -0.62
     Predators
    -0.62
    riel
    -0.62
     Pirates
    -0.58
    ampa
    -0.58
    POSITIVE LOGITS
     sections
    0.85
    ions
    0.84
    bare
    0.81
    meal
    0.81
    icals
    0.76
    alse
    0.76
    ttes
    0.75
    al
    0.74
    icles
    0.72
    isions
    0.72
    Act Density 0.017%

    No Known Activations