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

    Neuronpedia

    INDEX
    Explanations

    references to various types or categories

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -0.85
    LookAnd
    -0.82
    fjspx
    -0.75
    AutoField
    -0.74
    annica
    -0.71
    ″]
    -0.71
     незавершена
    -0.71
    +#+#
    -0.71
    帖最后由
    -0.71
     "}
    -0.71
    POSITIVE LOGITS
     Forster
    0.68
    ίο
    0.61
     Mahmud
    0.60
    illots
    0.60
     Mah
    0.60
     Mauro
    0.60
    MessageState
    0.60
    seiko
    0.59
     Isto
    0.58
    ><!--
    0.57
    Act Density 0.004%

    No Known Activations