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

    Neuronpedia

    INDEX
    Explanations

    references to "assumptions" and variations of that concept, often in a technical or formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enerys
    -0.62
    hedral
    -0.58
    IService
    -0.57
     Temples
    -0.55
    ruptedException
    -0.55
    Ferdin
    -0.55
    Tru
    -0.54
     GenerationType
    -0.53
     upra
    -0.53
    Redirection
    -0.53
    POSITIVE LOGITS
     ASS
    0.79
     Assets
    0.74
    клопе
    0.73
     asse
    0.70
    ASS
    0.70
    ConstraintMaker
    0.70
    ASSET
    0.69
     assets
    0.68
     ASSETS
    0.65
    Assets
    0.65
    Act Density 0.210%

    No Known Activations