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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal identity or self-reference

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WithIOException
    -0.61
    RenderAtEndOf
    -0.58
     Roskov
    -0.58
    发表于
    -0.57
    WriteBarrier
    -0.57
     doInBackground
    -0.57
     فريبيس
    -0.55
    NameInMap
    -0.54
    enumi
    -0.54
     springfox
    -0.54
    POSITIVE LOGITS
    ///</
    0.60
     meninos
    0.53
    setVerticalGroup
    0.52
     dégustation
    0.52
     Harrell
    0.50
     recommandée
    0.49
    szön
    0.48
    tiliz
    0.48
     externi
    0.47
     nemici
    0.47
    Act Density 0.015%

    No Known Activations