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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to characters, colors, and symbolic representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __*/
    -1.02
     Wallis
    -1.00
    AccessorTable
    -0.93
     Maul
    -0.91
     Bax
    -0.90
    IsContent
    -0.89
    ArrowToggle
    -0.88
    Географиясе
    -0.88
    appcompat
    -0.88
     Stras
    -0.86
    POSITIVE LOGITS
    ation
    0.74
     Mé
    0.69
    onClick
    0.67
     Jank
    0.66
    któ
    0.65
     Zamb
    0.64
     부
    0.63
    Ov
    0.62
    Liber
    0.61
     Mond
    0.61
    Act Density 1.820%

    No Known Activations