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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts and terms related to abstract formulations and assumptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inden
    -0.16
    ilog
    -0.15
     fame
    -0.14
    tep
    -0.14
    auer
    -0.13
    ctp
    -0.13
    unden
    -0.13
    ifa
    -0.13
    ibble
    -0.13
    wert
    -0.13
    POSITIVE LOGITS
     prior
    0.21
     assumptions
    0.20
     pri
    0.19
    prior
    0.18
     assumed
    0.17
     assumption
    0.17
     unspecified
    0.17
     underlying
    0.16
     Ass
    0.16
     additional
    0.16
    Act Density 0.397%

    No Known Activations