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

    Neuronpedia

    INDEX
    Explanations

    key concepts and terms related to theoretical frameworks in scientific literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     démission
    -0.68
     partea
    -0.68
     binoculars
    -0.64
     până
    -0.61
     apparti
    -0.60
     pouvaient
    -0.60
     affich
    -0.59
     laissant
    -0.59
     venait
    -0.58
     cantando
    -0.58
    POSITIVE LOGITS
    ^(@)
    0.99
    '},
    0.96
    []
    0.96
    fible
    0.96
    ".
    0.95
    )";
    0.94
    '],
    0.92
    ividual
    0.92
    )");
    0.91
    &
    0.91
    Act Density 3.720%

    No Known Activations