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

    Neuronpedia

    INDEX
    Explanations

    email addresses and identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.82
     diſt
    -0.79
     InputDecoration
    -0.78
     Reſ
    -0.77
    `,
    -0.76
     AssemblyTitle
    -0.74
     ſever
    -0.74
    UnsafeEnabled
    -0.72
    ſelf
    -0.72
     Verſ
    -0.71
    POSITIVE LOGITS
    +#+
    0.52
    6
    0.47
    3
    0.47
    1
    0.47
    2
    0.46
    9
    0.45
     who
    0.44
     whom
    0.44
     الرياضيه
    0.44
    7
    0.43
    Act Density 0.136%

    No Known Activations