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

    Neuronpedia

    INDEX
    Explanations

    negations or expressions of doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avía
    -0.72
    PageContext
    -0.69
    Étienne
    -0.62
    erati
    -0.62
    Gale
    -0.59
    AsUp
    -0.59
    cstdlib
    -0.58
    кота
    -0.58
     laun
    -0.57
    Randall
    -0.57
    POSITIVE LOGITS
     يتيمه
    1.02
     تانيه
    0.91
    حياته
    0.88
    fycat
    0.84
    poptosis
    0.82
    حياتها
    0.81
     الوطنيه
    0.81
     muſt
    0.79
     Guzman
    0.79
    
    0.79
    Act Density 0.244%

    No Known Activations