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

    Neuronpedia

    INDEX
    Explanations

    phrases that express knowledge or awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ero
    -0.18
    ids
    -0.17
    ucid
    -0.15
    ãĤīãģĦ
    -0.15
    ICLE
    -0.15
    aso
    -0.14
    andalone
    -0.14
    _kernel
    -0.14
     hav
    -0.14
    оÑģÑĤ
    -0.13
    POSITIVE LOGITS
    ledged
    0.30
    -how
    0.28
    led
    0.28
    æĻĵ
    0.26
    ledge
    0.25
    lege
    0.23
    ingly
    0.23
    LED
    0.21
     about
    0.20
    ledger
    0.18
    Act Density 0.116%

    No Known Activations