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

    Neuronpedia

    INDEX
    Explanations

    results indicating the validity and robustness of experimental findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.62
    tvguidetime
    -0.58
    lapsingToolbar
    -0.54
     légende
    -0.52
    Batis
    -0.50
    aarrggbb
    -0.49
     étoit
    -0.49
     eût
    -0.48
     fût
    -0.48
     colonnes
    -0.48
    POSITIVE LOGITS
    IndentedString
    0.84
    protoimpl
    0.61
     mergeFrom
    0.56
    sego
    0.53
    withIdentifier
    0.52
    IUrlHelper
    0.52
     BoxDecoration
    0.50
    Obrázky
    0.49
    maps
    0.49
    REFERRED
    0.49
    Act Density 0.175%

    No Known Activations