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

    Neuronpedia

    INDEX
    Explanations

    specific programming syntax and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.83
    C
    -0.78
    E
    -0.77
    P
    -0.77
     D
    -0.77
    K
    -0.75
     C
    -0.75
    B
    -0.73
     Cr
    -0.73
     N
    -0.72
    POSITIVE LOGITS
     myſelf
    1.61
     Monfieur
    1.56
     ſeveral
    1.49
     Jefus
    1.48
     raiſ
    1.46
     whoſe
    1.44
     themſelves
    1.43
     itſelf
    1.42
     iſt
    1.41
    ſelves
    1.40
    Act Density 0.291%

    No Known Activations