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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "to" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+#
    -1.00
    хьтан
    -0.94
    mybatisplus
    -0.93
    XmlAccessorType
    -0.84
     виправивши
    -0.82
     Мексичка
    -0.81
    UserScript
    -0.81
    GEBURTSDATUM
    -0.79
     AttributeSet
    -0.77
     ModelExpression
    -0.77
    POSITIVE LOGITS
    To
    1.81
     To
    1.75
    to
    1.06
     TO
    1.06
    TO
    1.02
    DataTo
    0.82
    setTo
    0.78
     Toh
    0.74
    toch
    0.70
    Чтобы
    0.68
    Act Density 0.161%

    No Known Activations