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

    Neuronpedia

    INDEX
    Explanations

    the word "and" in various contexts and forms

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.82
    MLLoader
    -0.80
     المعيارى
    -0.75
    NameInMap
    -0.73
     Houſe
    -0.71
    PreferredItem
    -0.70
    __':
    -0.70
     שוליים
    -0.69
     ſche
    -0.69
     Eſ
    -0.68
    POSITIVE LOGITS
    اریخ
    0.51
     let
    0.49
    let
    0.49
    intellij
    0.47
    tag
    0.47
    got
    0.47
    cube
    0.46
    asgi
    0.45
     guess
    0.44
     Andre
    0.43
    Act Density 0.185%

    No Known Activations