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

    Neuronpedia

    INDEX
    Explanations

    instances of the verb "to be" and its various conjugations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reeze
    -0.17
    iped
    -0.17
    _flight
    -0.14
    ç¥Ŀ
    -0.14
    iten
    -0.14
    .nano
    -0.14
    é£Ľ
    -0.13
    leet
    -0.13
    lt
    -0.13
    ãĤ¤ãĥĪ
    -0.13
    POSITIVE LOGITS
    isor
    0.15
     mix
    0.14
     Honest
    0.14
    [++
    0.14
    axon
    0.14
    .Plugin
    0.14
    ------+------+
    0.13
    feld
    0.13
     Roth
    0.13
    ibur
    0.13
    Act Density 0.335%

    No Known Activations