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

    Neuronpedia

    INDEX
    Explanations

    references to political positions or endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unky
    -0.14
    iry
    -0.14
     ActionTypes
    -0.14
     haut
    -0.14
    qe
    -0.14
    mÃŃt
    -0.14
    struk
    -0.14
    igham
    -0.13
    .AutoScale
    -0.13
    .Percent
    -0.13
    POSITIVE LOGITS
    ECH
    0.15
     Universal
    0.15
    337
    0.14
    à¹Ģà¸ĭ
    0.14
     envelopes
    0.14
    amb
    0.14
    loc
    0.13
    AML
    0.13
    izzo
    0.13
    le
    0.13
    Act Density 0.077%

    No Known Activations