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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "guess" and similar expressions indicating uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Demografía
    -0.83
     Roskov
    -0.82
    ]';
    -0.81
    Obrázky
    -0.81
    ViewFeatures
    -0.81
    щадь
    -0.79
     ?'
    -0.79
    hahahaha
    -0.78
    ковь
    -0.76
     kasarigan
    -0.76
    POSITIVE LOGITS
     decks
    0.96
     DECK
    0.95
     Deck
    0.88
    Deck
    0.85
     Decks
    0.84
     deck
    0.83
    deck
    0.78
     disappointed
    0.76
    frust
    0.73
     Frat
    0.69
    Act Density 0.051%

    No Known Activations