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

    Neuronpedia

    INDEX
    Explanations

    forms of the word "dead" or "die"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quin
    -0.17
    isbury
    -0.16
    ãĥĬãĥ«
    -0.16
    ÐĿÐIJ
    -0.16
     Duy
    -0.15
     IID
    -0.15
    jt
    -0.15
    iece
    -0.15
    315
    -0.14
    JD
    -0.14
    POSITIVE LOGITS
     d
    0.25
    ầu
    0.17
     Chin
    0.16
    chia
    0.15
     dn
    0.14
    aleur
    0.14
    rier
    0.14
    enna
    0.14
    lek
    0.14
    empo
    0.14
    Act Density 0.024%

    No Known Activations