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

    Neuronpedia

    INDEX
    Explanations

    references to classic literature or film adaptations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     single
    -0.49
     electrically
    -0.48
    single
    -0.46
     bit
    -0.43
     agreed
    -0.43
    Cuen
    -0.42
    amaran
    -0.42
     Dogg
    -0.41
     Madras
    -0.41
     peasant
    -0.41
    POSITIVE LOGITS
    Geplaatst
    0.71
    μως
    0.68
    BASEPATH
    0.64
     Roskov
    0.64
    цездатний
    0.63
    ervlak
    0.63
    afficheront
    0.62
    EDEFAULT
    0.62
    aarrggbb
    0.62
    contentLoaded
    0.61
    Act Density 0.059%

    No Known Activations