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

    Neuronpedia

    INDEX
    Explanations

    assertions or claims that indicate changes or results over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.92
    InjectAttribute
    -0.85
     cdti
    -0.81
    ConstraintMaker
    -0.78
     Reſ
    -0.77
     thereon
    -0.77
     NDEBUG
    -0.76
     ſtate
    -0.75
     Jefus
    -0.74
     ModelExpression
    -0.74
    POSITIVE LOGITS
     happen
    0.68
     happening
    0.66
     done
    0.62
     happened
    0.59
     happens
    0.57
     a
    0.52
    MenuView
    0.50
     leads
    0.49
     terjadi
    0.46
     allemaal
    0.45
    Act Density 0.238%

    No Known Activations