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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "over" followed by a numerical value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assin
    -0.15
    ycz
    -0.14
    inalg
    -0.14
    TextNode
    -0.14
    ugal
    -0.14
    cosity
    -0.14
    οÏįν
    -0.14
    ãģĨãģ¡
    -0.14
    undler
    -0.14
    elib
    -0.13
    POSITIVE LOGITS
     dozen
    0.18
    900
    0.16
    400
    0.15
    ä¹İ
    0.15
    700
    0.15
    0.15
     thousands
    0.14
    600
    0.14
     thousand
    0.14
    dup
    0.13
    Act Density 0.034%

    No Known Activations