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

    Neuronpedia

    INDEX
    Explanations

    evidence and references concerning scientific findings and results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     női
    -0.65
    ++]=
    -0.60
    ]+=
    -0.53
    )))));
    -0.52
     automatiques
    -0.51
     compréhen
    -0.49
     charging
    -0.49
    haustible
    -0.49
    клопе
    -0.48
    ברת
    -0.48
    POSITIVE LOGITS
     will
    1.24
     would
    1.18
     could
    1.12
     may
    1.11
     is
    1.10
     can
    1.03
     might
    0.98
     was
    0.96
     has
    0.93
     should
    0.93
    Act Density 2.272%

    No Known Activations