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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases that suggest choice or desire

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utters
    -0.16
    ãĤ¢ãĥ¼
    -0.15
    egl
    -0.15
    ubat
    -0.15
     defaultMessage
    -0.15
    eker
    -0.14
    ấp
    -0.14
    UDA
    -0.14
    кÑĤа
    -0.14
     XCT
    -0.14
    POSITIVE LOGITS
    /gtest
    0.15
    uch
    0.14
    èĪ
    0.14
     abi
    0.14
    oted
    0.14
     Gone
    0.14
    FK
    0.14
     Abram
    0.14
     paid
    0.13
    .framework
    0.13
    Act Density 0.217%

    No Known Activations