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

    Neuronpedia

    INDEX
    Explanations

    references to various institutes and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mâ
    -0.83
     diffe
    -0.77
     Suz
    -0.77
     Mercan
    -0.74
     Poliz
    -0.74
    barung
    -0.74
     Phry
    -0.73
    ToMany
    -0.73
     Manus
    -0.71
     Papua
    -0.70
    POSITIVE LOGITS
     Institute
    2.19
     institute
    1.96
     institutes
    1.91
    Institute
    1.87
     INSTITUTE
    1.82
     Institutes
    1.80
    institute
    1.73
     Institut
    1.27
     instituto
    1.20
     INSTIT
    1.18
    Act Density 0.050%

    No Known Activations