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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "lever" and related terms indicating its use in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.17
    缮çļĦ
    -0.15
    awa
    -0.15
    okit
    -0.14
    AttributeValue
    -0.14
    ocr
    -0.14
    ami
    -0.14
    µľ
    -0.14
    iol
    -0.14
    ramer
    -0.14
    POSITIVE LOGITS
    129
    0.17
    itler
    0.16
    364
    0.14
    630
    0.14
    è¨Ģãģ£ãģ¦
    0.14
    ocities
    0.14
    ãĥ¼ãĥ¬
    0.14
    AXB
    0.14
    ÑĢÑı
    0.14
    bars
    0.14
    Act Density 0.007%

    No Known Activations