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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating repetition or excessiveness

    oai_token-act-pair · gpt-3.5-turbo

    the repetitive use of the word "over" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arium
    -0.78
    illary
    -0.72
     Lauder
    -0.70
    UES
    -0.68
    ORY
    -0.68
    UE
    -0.67
    uum
    -0.65
    ãĤ´
    -0.64
    =-=-=-=-
    -0.62
    ittal
    -0.61
    POSITIVE LOGITS
    hang
    1.19
    drive
    1.14
    loading
    1.07
    haul
    1.01
    priced
    1.01
    grown
    0.99
    tones
    0.98
    lord
    0.97
    lay
    0.97
    lander
    0.95
    Act Density 0.081%

    No Known Activations