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

    Neuronpedia

    INDEX
    Explanations

    references to prizes and bonuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AspNetCore
    -0.93
    JspWriter
    -0.78
    andaş
    -0.73
    EndTag
    -0.72
    complexType
    -0.71
    LookAnd
    -0.69
    PyExc
    -0.68
     pantalon
    -0.68
    stateProvider
    -0.68
    ircut
    -0.67
    POSITIVE LOGITS
     delight
    0.94
     TREAS
    0.90
     Schatz
    0.89
     joys
    0.88
     trésor
    0.86
     Pleasure
    0.85
     treasure
    0.85
     pleasure
    0.79
     delights
    0.78
     Bonus
    0.78
    Act Density 0.082%

    No Known Activations