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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their representations in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     članak
    -0.59
     ViewController
    -0.56
    ⁦
    -0.56
    RefNanny
    -0.56
     Sein
    -0.56
     Fris
    -0.56
    Herr
    -0.55
    `]
    -0.54
    hiza
    -0.54
     zw
    -0.54
    POSITIVE LOGITS
    subsubsection
    1.08
    subsection
    0.99
     itſelf
    0.78
     pleaſure
    0.76
    +#+#
    0.75
     myſelf
    0.75
     ſte
    0.73
     sûr
    0.72
     Jefus
    0.71
     Moderato
    0.69
    Act Density 0.352%

    No Known Activations