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

    Neuronpedia

    INDEX
    Explanations

    phrases related to passage of time or chronological sequences

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "Over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arium
    -0.70
    BILITY
    -0.70
    osphere
    -0.66
    ittal
    -0.66
    ude
    -0.64
    uary
    -0.60
     understatement
    -0.59
    BLE
    -0.59
    女
    -0.59
    udes
    -0.59
    POSITIVE LOGITS
    whelming
    1.18
    lap
    1.05
    haul
    1.03
    whel
    1.03
    hang
    1.02
    lay
    1.00
    ride
    0.98
    flow
    0.96
    statement
    0.95
    lying
    0.95
    Act Density 0.032%

    No Known Activations