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

    Neuronpedia

    INDEX
    Explanations

    first-person pronouns and expressions of personal opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uin
    -0.08
    ãĥ³ãĥIJ
    -0.07
    ìļķ
    -0.07
    -liter
    -0.07
     знаÑĤÑĮ
    -0.07
     isNaN
    -0.07
     гÑĥб
    -0.07
     è¦ģ
    -0.07
    OOM
    -0.07
    .WriteByte
    -0.07
    POSITIVE LOGITS
     expect
    0.12
     expecting
    0.11
     expectation
    0.10
     expects
    0.10
     Expect
    0.10
    Expect
    0.10
    expect
    0.09
     expectations
    0.09
     think
    0.09
     expected
    0.09
    Act Density 0.023%

    No Known Activations