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

    Neuronpedia

    INDEX
    Explanations

    terms related to elimination or extinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orb
    -0.15
    iler
    -0.15
    ìĹ´
    -0.15
    cot
    -0.14
    md
    -0.14
    stri
    -0.14
    loth
    -0.14
    OLUMN
    -0.14
    ifu
    -0.14
     riêng
    -0.14
    POSITIVE LOGITS
    æ»ħ
    0.18
    æİī
    0.17
     Zy
    0.17
    CACHE
    0.16
    /null
    0.15
    wipe
    0.15
    angers
    0.14
    VED
    0.14
    enders
    0.14
    esktop
    0.14
    Act Density 0.072%

    No Known Activations