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

    Neuronpedia

    INDEX
    Explanations

    instances of factual statements or claims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -1.04
    windowFixed
    -0.82
    antaranya
    -0.79
    extAlignment
    -0.78
    AntiForgeryToken
    -0.78
    PhysRevLett
    -0.71
    UVWXYZ
    -0.71
     متعلقه
    -0.71
    kháu
    -0.69
    msgTypes
    -0.68
    POSITIVE LOGITS
     actually
    0.91
    actually
    0.71
     egentlig
    0.70
    Actually
    0.70
     Actually
    0.68
     ACTUALLY
    0.59
     eigentlich
    0.58
     even
    0.55
     egentligen
    0.54
     quite
    0.53
    Act Density 0.306%

    No Known Activations