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

    Neuronpedia

    INDEX
    Explanations

    the word "This" and phrases indicating the beginning of a statement or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isty
    -0.17
    vale
    -0.17
    ëĭ¹
    -0.16
    acht
    -0.14
    adi
    -0.14
    abis
    -0.14
    berger
    -0.14
    esco
    -0.14
    _goal
    -0.14
    èĬ¸
    -0.14
    POSITIVE LOGITS
     course
    0.18
     week
    0.18
    amps
    0.17
     article
    0.16
     listing
    0.16
     weeks
    0.15
     episode
    0.15
     pack
    0.15
     topic
    0.15
    ·
    0.15
    Act Density 0.225%

    No Known Activations