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

    Neuronpedia

    INDEX
    Explanations

    references to specific numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REP
    -0.15
    edicine
    -0.14
    isphere
    -0.14
    ersist
    -0.14
    olume
    -0.13
     apart
    -0.13
    aan
    -0.13
    SCAN
    -0.13
    istrat
    -0.13
    esini
    -0.13
    POSITIVE LOGITS
    üçük
    0.16
    æ¨
    0.16
    herits
    0.15
    оÑģÑĤÑĮ
    0.15
    UPER
    0.15
    hoot
    0.15
    .Void
    0.15
    _VOID
    0.14
    /sources
    0.14
    ëĿ½
    0.14
    Act Density 0.004%

    No Known Activations