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

    Neuronpedia

    INDEX
    Explanations

    references to monetary values or currencies in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scenes
    -0.62
     kasarigan
    -0.56
     Lu
    -0.55
     판
    -0.54
     scenario
    -0.53
     walk
    -0.53
     works
    -0.53
     graduating
    -0.53
     cry
    -0.52
     visually
    -0.52
    POSITIVE LOGITS
     Reſ
    0.54
     Taktlose
    0.52
     zijne
    0.52
     ſtill
    0.51
     Perſ
    0.49
     Administrativna
    0.48
     naturen
    0.48
    $
    0.47
     feroit
    0.47
     ſol
    0.47
    Act Density 0.599%

    No Known Activations