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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal attributes, classifications, and statistical data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    veaux
    -0.58
    RenderAtEndOf
    -0.58
    "];
    -0.57
    +
    -0.56
    pyplot
    -0.55
     ||
    -0.54
    -0.54
     которое
    -0.53
    "])

    -0.52
    ⇑
    -0.52
    POSITIVE LOGITS
     avoient
    0.84
     houſe
    0.83
     argint
    0.82
    quisa
    0.82
     marquées
    0.81
     Вікі
    0.81
     pleaſure
    0.81
     foncé
    0.81
     Inscrivez
    0.80
     désol
    0.80
    Act Density 0.514%
    No Known Activations