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

    Neuronpedia

    INDEX
    Explanations

    references to statistical measurements or indices

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Drog
    -0.78
    NameInMap
    -0.77
     ROG
    -0.69
    Hamlet
    -0.69
     EMB
    -0.69
     Sheeran
    -0.68
    Darm
    -0.67
    Gamer
    -0.67
     Eman
    -0.67
    вЂ
    -0.67
    POSITIVE LOGITS
     INDEX
    1.13
     getIndex
    1.12
     indices
    1.02
     Index
    1.01
     index
    0.96
    Indices
    0.93
     indexes
    0.93
    INDEX
    0.91
    cellaneous
    0.89
     indexing
    0.89
    Act Density 0.005%

    No Known Activations