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

    Neuronpedia

    INDEX
    Explanations

    concessive conjunctions that indicate conditions or contrasting statements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    thanes
    -0.52
    anho
    -0.48
    UTERS
    -0.44
     kul
    -0.43
     terle
    -0.42
    apart
    -0.42
    lında
    -0.41
    sequelize
    -0.40
     Tribune
    -0.40
     запла
    -0.40
    POSITIVE LOGITS
    __(/*!
    0.85
    RectangleBorder
    0.83
     kasarigan
    0.82
    /*
    0.75
     kaynağından
    0.74
    rrggbb
    0.72
    CloseOperation
    0.69
    \{\\
    0.68
     """
    0.68
     Goi
    0.67
    Act Density 0.028%

    No Known Activations