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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific animated TV show

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.49
     McNally
    -0.46
     Burroughs
    -0.46
    película
    -0.46
    庐
    -0.46
     Felton
    -0.45
     Kaye
    -0.44
    NgModule
    -0.44
    audiovisuel
    -0.44
     ny
    -0.43
    POSITIVE LOGITS
     Simpsons
    1.18
     Simpson
    1.11
     simpsons
    1.05
     Bart
    1.04
     Homer
    1.00
    Simpson
    0.98
    Bart
    0.95
    Homer
    0.95
     simpson
    0.95
     Springfield
    0.89
    Act Density 0.231%

    No Known Activations