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

    Neuronpedia

    INDEX
    Explanations

    specific high-frequency keywords or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Patri
    -0.16
     Brothers
    -0.15
     otherwise
    -0.15
    otherwise
    -0.14
    305
    -0.14
    ubber
    -0.14
    خر
    -0.14
    (rad
    -0.14
     Rap
    -0.14
     Rebel
    -0.14
    POSITIVE LOGITS
    oba
    0.18
    etting
    0.15
    gio
    0.15
    оба
    0.15
    ogne
    0.15
    ãĥĶãĥ¼
    0.14
    ема
    0.14
    ertas
    0.14
    okud
    0.14
    lige
    0.14
    Act Density 0.010%

    No Known Activations