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

    Neuronpedia

    INDEX
    Explanations

    phrases related to potential actions, preferences, or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pyplot
    -0.54
     Figura
    -0.54
    sext
    -0.52
     واج
    -0.50
    ostock
    -0.50
    zur
    -0.49
     Sext
    -0.48
     yarar
    -0.47
     göre
    -0.47
     Awak
    -0.46
    POSITIVE LOGITS
    <bos>
    1.20
    hoeddwyd
    0.88
    featureID
    0.88
    الإنجليزية
    0.87
     unknownFields
    0.85
     ModelExpression
    0.81
    tvguidetime
    0.80
    IsMutable
    0.78
    fjspx
    0.78
    +#+
    0.77
    Act Density 0.078%

    No Known Activations