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

    Neuronpedia

    INDEX
    Explanations

    words expressing exclusivity or limitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    brates
    -0.16
    rek
    -0.15
    elight
    -0.15
    ja
    -0.15
    ahan
    -0.14
    ri
    -0.14
     cert
    -0.14
    kir
    -0.14
    me
    -0.14
    Äįi
    -0.14
    POSITIVE LOGITS
    FTA
    0.17
    iol
    0.17
    ropri
    0.17
    ırak
    0.16
    halb
    0.15
    iggs
    0.15
    /sdk
    0.15
    DTV
    0.15
    AccessException
    0.14
    ecause
    0.14
    Act Density 0.096%

    No Known Activations