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

    Neuronpedia

    INDEX
    Explanations

    instructions or statements involving a variable assignment in mathematical or programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     d
    -0.47
     ex
    -0.46
    </em>
    -0.45
     ch
    -0.43
    ↵↵
    -0.43
     I
    -0.42
     g
    -0.41
     po
    -0.41
     esta
    -0.41
     Gross
    -0.40
    POSITIVE LOGITS
     Reſ
    0.97
     myſelf
    0.95
     houſe
    0.94
     pleaſure
    0.94
    AndEndTag
    0.93
    0.93
     Jefus
    0.92
    Datuak
    0.91
     faſt
    0.91
     raiſ
    0.90
    Act Density 0.035%

    No Known Activations