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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or questioning assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -1.02
    Personendaten
    -0.99
    دانشنامهٔ
    -0.91
    Personensuche
    -0.91
    AccessorTable
    -0.87
    contentLoaded
    -0.84
    RunWith
    -0.84
     surla
    -0.83
     تكبرها
    -0.83
    "},
    -0.81
    POSITIVE LOGITS
     Numerade
    0.53
     ennemis
    0.52
     craindre
    0.49
     Bogen
    0.47
    Standalone
    0.46
     vierge
    0.45
    Restriction
    0.45
    intra
    0.44
    NORE
    0.43
     esconder
    0.42
    Act Density 0.194%

    No Known Activations