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

    Neuronpedia

    INDEX
    Explanations

    terms related to permissions, abilities, and perceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awn
    -0.16
    íıIJ
    -0.16
    spin
    -0.15
    -quarters
    -0.15
    ersh
    -0.15
    ÑĢг
    -0.15
    wargs
    -0.15
    dır
    -0.15
    urge
    -0.15
    gger
    -0.15
    POSITIVE LOGITS
    /per
    0.22
    shire
    0.21
    imeter
    0.21
    mutations
    0.20
    pendicular
    0.20
     capita
    0.20
    iphery
    0.19
    ance
    0.18
    ceived
    0.18
    _GRANTED
    0.17
    Act Density 0.050%

    No Known Activations