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

    Neuronpedia

    INDEX
    Explanations

    mentions of numerical limits or restrictions

    oai_token-act-pair · gpt-3.5-turbo

    numerical limits or restrictions related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sketch
    -0.69
    JS
    -0.65
     partName
    -0.62
    ruary
    -0.62
     NEWS
    -0.61
    CONCLUS
    -0.60
    wow
    -0.60
    Conclusion
    -0.60
     Task
    -0.59
    comings
    -0.57
    POSITIVE LOGITS
     maximum
    1.18
     allowable
    1.11
    maximum
    1.04
    Maximum
    1.03
     unlimited
    1.03
     Maximum
    0.89
     limit
    0.89
     allowed
    0.87
     whichever
    0.87
     permitted
    0.86
    Act Density 0.193%

    No Known Activations