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

    Neuronpedia

    INDEX
    Explanations

    statements and assertions about significant topics or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stdc
    -0.48
     BitmapFactory
    -0.46
     кӀ
    -0.45
    ImageContext
    -0.44
    appcompat
    -0.43
    elif
    -0.43
    WireFormatLite
    -0.42
     Trust
    -0.42
    好不容易
    -0.41
    ]--;
    -0.41
    POSITIVE LOGITS
     really
    0.84
     verdaderamente
    0.81
     eigentliche
    0.80
    essentiel
    0.79
     véritable
    0.76
    真正
    0.75
    really
    0.75
     truly
    0.74
     intéressant
    0.73
     REALLY
    0.73
    Act Density 0.257%

    No Known Activations