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

    Neuronpedia

    INDEX
    Explanations

    references to options and choices available in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Makoto
    -0.76
     epile
    -0.75
    euse
    -0.74
     кӀош
    -0.73
     &___
    -0.72
     vuitton
    -0.71
     NgModule
    -0.69
    قایناق‌لار
    -0.69
     Kisses
    -0.69
    SharedDtor
    -0.69
    POSITIVE LOGITS
     alternatives
    0.98
     options
    0.88
    alternatives
    0.85
    Alternatives
    0.83
     alternative
    0.77
     Alternatives
    0.75
     opciones
    0.73
     alternativas
    0.73
     alternatif
    0.73
     opzioni
    0.71
    Act Density 0.020%

    No Known Activations