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

    Neuronpedia

    INDEX
    Explanations

    topics related to legal and procedural processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ader
    -0.15
    ROKE
    -0.15
     MAK
    -0.14
    ubb
    -0.14
     Erot
    -0.14
    ruba
    -0.14
    handling
    -0.14
     kako
    -0.14
    ichert
    -0.14
     bordel
    -0.14
    POSITIVE LOGITS
     instead
    0.23
     Instead
    0.19
     introduce
    0.17
    Instead
    0.17
     Desc
    0.17
    instead
    0.16
     introduces
    0.16
     introdu
    0.16
    reate
    0.15
     use
    0.15
    Act Density 0.110%

    No Known Activations