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

    Neuronpedia

    INDEX
    Explanations

    concepts and terminology related to data classification and the simplification of complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.16
    agal
    -0.15
    rong
    -0.14
     jack
    -0.14
    vap
    -0.14
    ॰
    -0.14
    ersh
    -0.14
    iš
    -0.13
    jack
    -0.13
     é¢
    -0.13
    POSITIVE LOGITS
     assumed
    0.28
     assume
    0.24
     assum
    0.23
     assumption
    0.23
     assumes
    0.23
     here
    0.21
     Ass
    0.20
    assume
    0.20
     Assume
    0.20
     throughout
    0.20
    Act Density 0.217%

    No Known Activations