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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns and measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to amounts or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheless
    -0.70
     citiz
    -0.70
    ©¶æ
    -0.68
     newcom
    -0.65
    theless
    -0.64
     Citiz
    -0.62
     ende
    -0.61
     streng
    -0.61
     enthusi
    -0.61
    ortunately
    -0.60
    POSITIVE LOGITS
    .
    1.21
    %.
    0.71
    ._
    0.69
    %;
    0.67
    izons
    0.67
    *.
    0.65
    ./
    0.65
    .<
    0.65
    ½
    0.65
    .''.
    0.64
    Act Density 0.095%

    No Known Activations