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

    Neuronpedia

    INDEX
    Explanations

    terms related to estimates or estimations of values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Nah
    -0.15
    ullo
    -0.15
    è¡¡
    -0.14
    otas
    -0.14
    linger
    -0.14
    agher
    -0.14
    VENTORY
    -0.14
    лаб
    -0.13
    inery
    -0.13
    agers
    -0.13
    POSITIVE LOGITS
    hod
    0.16
    ktop
    0.15
    ηÏĤ
    0.15
    hood
    0.14
    edl
    0.14
    _tac
    0.14
    dom
    0.14
    éĵģ
    0.14
    lier
    0.14
     Irvine
    0.14
    Act Density 0.011%

    No Known Activations