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

    Neuronpedia

    INDEX
    Explanations

    formatted variable declarations and expressions commonly used in programming languages, particularly in template literals or string interpolation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.93
     Theſe
    -0.84
     purpoſe
    -0.80
     Efq
    -0.80
     Majefty
    -0.77
     myſelf
    -0.77
     Jefus
    -0.76
     himſelf
    -0.76
     ſeveral
    -0.76
     themſelves
    -0.71
    POSITIVE LOGITS
     nakalista
    0.54
    TacToe
    0.54
    ­
    0.52
     createState
    0.47
    argout
    0.46
    /***/
    0.44
    Obrázky
    0.43
    </b>
    0.42
    GGLE
    0.42
    qrstuvwxyz
    0.42
    Act Density 0.177%

    No Known Activations