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

    Neuronpedia

    INDEX
    Explanations

    terms related to power levels in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essim
    -0.18
    egl
    -0.15
    emies
    -0.14
    opoulos
    -0.14
    åĴ¨
    -0.13
     GPLv
    -0.13
    ypo
    -0.13
     ÙĪØ£ÙĨ
    -0.13
    οÏħÏģγ
    -0.13
    -half
    -0.13
    POSITIVE LOGITS
     pension
    0.17
     пен
    0.16
    Fx
    0.16
    folio
    0.15
    erton
    0.15
    uci
    0.15
    ãĥ«ãĤ¯
    0.15
    .asp
    0.14
    jak
    0.14
     Cres
    0.14
    Act Density 0.026%

    No Known Activations