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

    Neuronpedia

    INDEX
    Explanations

    quantitative data related to counts and totals

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.44
     is
    -0.41
     string
    -0.41
     V
    -0.39
     the
    -0.39
     
    -0.38
     or
    -0.37
     en
    -0.37
     part
    -0.36
     em
    -0.36
    POSITIVE LOGITS
    IVEREF
    1.00
     '\\;'
    0.98
     nakalista
    0.96
    enumi
    0.94
    ViewImports
    0.93
    InitVars
    0.93
    MigrationBuilder
    0.93
     betweenstory
    0.93
    Datuak
    0.92
    +#+#
    0.90
    Act Density 0.108%

    No Known Activations