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

    Neuronpedia

    INDEX
    Explanations

    periods at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically periods indicating the end of a statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iannopoulos
    -0.85
    ahime
    -0.78
    stanbul
    -0.74
    imus
    -0.72
    oso
    -0.72
    orp
    -0.68
    idis
    -0.67
    arna
    -0.67
    cream
    -0.66
    gren
    -0.66
    POSITIVE LOGITS
     Habit
    0.82
    ²¾
    0.81
     attraction
    0.70
     capita
    0.68
     haunted
    0.63
    Ħ¢
    0.61
    duction
    0.61
    hibition
    0.60
     Manit
    0.60
     curiosity
    0.59
    Act Density 0.000%

    No Known Activations