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

    Neuronpedia

    INDEX
    Explanations

    references to legal frameworks and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lone
    -0.17
     types
    -0.15
    ysi
    -0.15
    emsp
    -0.15
     kinds
    -0.15
    волÑı
    -0.15
     disparate
    -0.14
     nation
    -0.14
     Types
    -0.14
    ohl
    -0.14
    POSITIVE LOGITS
    oric
    0.21
    ese
    0.20
     hereby
    0.20
     mentioned
    0.20
    orie
    0.18
    orical
    0.18
    tas
    0.16
    undle
    0.16
     whole
    0.16
     analyzes
    0.15
    Act Density 0.401%

    No Known Activations