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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements and evaluations over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ent
    -0.55
     .
    -0.55
    <eos>
    -0.52
    FP
    -0.48
    BA
    -0.46
     Francisco
    -0.46
    </i>
    -0.46
    ·
    -0.46
     working
    -0.46
    /
    -0.45
    POSITIVE LOGITS
    ViewFeatures
    0.84
    featureID
    0.80
    styleType
    0.80
     becauſe
    0.74
     itſelf
    0.74
     ExecuteAsync
    0.73
     >=",
    0.68
    cuma
    0.67
     typelib
    0.67
    WebServlet
    0.66
    Act Density 0.446%

    No Known Activations