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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    威
    -0.44
    aarrggbb
    -0.44
     dérou
    -0.43
    "]];
    -0.43
    しん
    -0.43
    مان
    -0.42
    боро
    -0.42
    hank
    -0.42
     pertinentes
    -0.42
    fjspx
    -0.41
    POSITIVE LOGITS
    annica
    0.79
    Portail
    0.72
     propOrder
    0.71
     firebaseConfig
    0.69
    NewGuid
    0.68
    égard
    0.65
    Portály
    0.65
    Kaieteur
    0.65
     whoſe
    0.61
    XmlAccessorType
    0.61
    Act Density 0.007%

    No Known Activations