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

    Neuronpedia

    INDEX
    Explanations

    concepts related to policies and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dge
    -0.17
    urgeon
    -0.15
    ifs
    -0.15
    HR
    -0.14
    iel
    -0.14
    ienne
    -0.14
    BackPressed
    -0.14
    iagnostics
    -0.14
     Bris
    -0.14
     Stall
    -0.13
    POSITIVE LOGITS
    ÏĦÏīν
    0.17
     TRACE
    0.15
     Trace
    0.15
    astr
    0.15
    ernet
    0.14
    ække
    0.14
    aleza
    0.14
     Bucket
    0.14
    orsk
    0.14
    _species
    0.14
    Act Density 0.041%

    No Known Activations