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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values and percentages in experimental procedures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.16
    MigrationBuilder
    -1.12
     Италијани
    -1.10
    LookAnd
    -1.05
     propOrder
    -1.02
    InjectAttribute
    -1.00
     unknownFields
    -0.99
    ⓧ
    -0.99
     Italijanski
    -0.98
     beginnetje
    -0.98
    POSITIVE LOGITS
     a
    0.56
    maxsize
    0.50
    avia
    0.48
     in
    0.48
     ten
    0.46
    ly
    0.45
     an
    0.45
     common
    0.45
     basic
    0.44
     comparable
    0.43
    Act Density 0.031%

    No Known Activations