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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming syntax and code structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -0.89
    ſelf
    -0.83
     themſelves
    -0.83
    ſelves
    -0.81
     Efq
    -0.78
     raiſ
    -0.77
    "]));
    -0.77
     ſtate
    -0.75
     himſelf
    -0.75
     chofe
    -0.75
    POSITIVE LOGITS
     I
    0.44
     beispiel
    0.43
     and
    0.43
    StructEnd
    0.41
     ver
    0.41
     AND
    0.41
     :
    0.41
    имо
    0.40
    encanaan
    0.40
     ::
    0.40
    Act Density 0.356%

    No Known Activations