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

    Neuronpedia

    INDEX
    Explanations

    hyperlinked elements or references in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -1.10
    تقاوى
    -1.07
    dafx
    -1.04
    CppMethod
    -1.03
     HasFactory
    -0.98
    +#+
    -0.94
    PyExc
    -0.94
    MigrationBuilder
    -0.94
    RenderAtEndOf
    -0.90
     unknownFields
    -0.90
    POSITIVE LOGITS
    <eos>
    0.48
    ↵↵
    0.48
    ↵
    0.44
     Global
    0.43
     A
    0.43
     c
    0.42
     positive
    0.42
    p
    0.42
     <
    0.42
     
    0.42
    Act Density 0.006%

    No Known Activations