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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate clarification or specification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VERR
    -0.17
    ÏīÏĤ
    -0.15
    rib
    -0.14
    teenth
    -0.13
    edback
    -0.13
    дÑĢеÑģ
    -0.13
    OX
    -0.13
    íĮħ
    -0.13
    ηÏĤ
    -0.13
    rin
    -0.13
    POSITIVE LOGITS
    atre
    0.20
    adays
    0.17
    fare
    0.17
    oret
    0.17
    bidden
    0.15
    oline
    0.15
     Fare
    0.15
     fare
    0.15
    laps
    0.14
    åĬŁ
    0.14
    Act Density 0.146%

    No Known Activations