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

    Neuronpedia

    INDEX
    Explanations

    statements and concepts related to promises and commitments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MOTE
    -0.16
    bios
    -0.15
    ikel
    -0.15
    dec
    -0.15
    amac
    -0.15
     Ñĥз
    -0.15
    oled
    -0.14
    fbe
    -0.14
    lz
    -0.14
    иÑģÑģ
    -0.14
    POSITIVE LOGITS
     promises
    0.21
     promise
    0.17
     vows
    0.17
    getti
    0.16
     pledges
    0.16
    ģı
    0.16
    ISC
    0.15
     رÙģع
    0.15
     vow
    0.14
    promise
    0.14
    Act Density 0.200%

    No Known Activations