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

    Neuronpedia

    INDEX
    Explanations

    programming functions and error handling assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aux
    -0.14
    eros
    -0.14
    inx
    -0.14
    unks
    -0.14
    /npm
    -0.13
    gard
    -0.13
    etta
    -0.13
    ired
    -0.13
    =null
    -0.13
    :nil
    -0.13
    POSITIVE LOGITS
     expected
    0.27
     expect
    0.25
     expectations
    0.24
     EXPECT
    0.24
     Expected
    0.23
     expectation
    0.23
    expected
    0.22
    (expected
    0.21
     Expect
    0.21
    Expect
    0.19
    Act Density 0.053%

    No Known Activations