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

    Neuronpedia

    INDEX
    Explanations

    sentences structured as a command or directive

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant numbers or results in various contexts, often related to politics, campaigns, and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrap
    -0.58
     Pag
    -0.53
     Hollow
    -0.51
     pursue
    -0.48
     equip
    -0.48
     entirely
    -0.48
     final
    -0.48
     pursuing
    -0.47
     Breed
    -0.46
    uca
    -0.46
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    0.91
    ³³³³
    0.90
    ³³³³³³³³
    0.84
    ³³³
    0.83
    inav
    0.70
    âĶĢâĶĢâĶĢâĶĢ
    0.68
    ³³
    0.67
    Anyway
    0.66
    Rating
    0.65
    Article
    0.64
    Act Density 1.071%

    No Known Activations