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

    Neuronpedia

    INDEX
    Explanations

    concepts related to identity and societal roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     remaining
    -0.49
     actual
    -0.48
     existing
    -0.45
    assert
    -0.43
     utafitiHapana
    -0.43
     rango
    -0.42
    比
    -0.42
     actually
    -0.41
     Sonne
    -0.41
    у
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.91
     /\.(
    0.80
    ]")]
    0.79
    Revenir
    0.76
     BoxDecoration
    0.75
    AutoScaleMode
    0.72
    parsedMessage
    0.72
    bcryptjs
    0.72
    Hochspringen
    0.71
     ArrayAdapter
    0.69
    Act Density 0.830%

    No Known Activations