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

    Neuronpedia

    INDEX
    Explanations

    references to "Lie" related to mathematical concepts or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    lie type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    afone
    -0.56
     Kina
    -0.44
    jątk
    -0.44
    webElementGuid
    -0.42
     foss
    -0.42
    CardModule
    -0.41
    ţilor
    -0.41
    很難
    -0.40
    RTEX
    -0.40
     Quell
    -0.40
    POSITIVE LOGITS
     Lie
    2.47
    Lie
    2.34
    lie
    2.27
     lie
    2.22
     LIE
    1.95
    LIE
    1.77
     lies
    1.26
     Lies
    1.20
    Lies
    1.13
     Lieberman
    1.07
    Act Density 0.005%

    No Known Activations