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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "some."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    robe
    -0.17
     pij
    -0.16
    Occurred
    -0.15
    omor
    -0.15
    ping
    -0.15
    omu
    -0.14
    pis
    -0.14
    arning
    -0.14
    uum
    -0.14
    imeter
    -0.14
    POSITIVE LOGITS
     even
    0.18
    est
    0.17
    body
    0.17
     parts
    0.16
    -times
    0.16
    place
    0.16
    even
    0.15
    جار
    0.15
     such
    0.15
    ones
    0.15
    Act Density 0.080%

    No Known Activations