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

    Neuronpedia

    INDEX
    Explanations

    syntax elements related to code or programming structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Ver
    -0.57
     A
    -0.54
    ↵↵
    -0.54
     B
    -0.54
     F
    -0.53
     S
    -0.53
     all
    -0.50
     Far
    -0.50
     At
    -0.50
     the
    -0.49
    POSITIVE LOGITS
     Anſ
    1.07
     Majefty
    1.02
     Reſ
    1.01
     doubtnut
    1.00
     purpoſe
    0.97
     auffi
    0.96
     ſtate
    0.91
     himſelf
    0.90
    ſelf
    0.90
     raiſ
    0.90
    Act Density 0.001%

    No Known Activations