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

    Neuronpedia

    INDEX
    Explanations

    the word "to" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rente
    -0.15
    loha
    -0.15
    Ĭ¶
    -0.15
    ARAM
    -0.14
    implify
    -0.14
    гоÑĤ
    -0.14
    oras
    -0.13
    reece
    -0.13
    shuffle
    -0.13
     NOT
    -0.13
    POSITIVE LOGITS
     be
    0.17
     Laur
    0.17
    -know
    0.16
     know
    0.15
    cher
    0.15
    меÑĤÑĮ
    0.15
    åѦä¼ļ
    0.14
    563
    0.14
    873
    0.14
    ering
    0.14
    Act Density 0.043%

    No Known Activations