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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "following."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULA
    -0.17
    sein
    -0.17
    /packages
    -0.14
     cin
    -0.14
    ãĥ«ãĥī
    -0.14
    leet
    -0.14
    sel
    -0.14
     дÑĥ
    -0.14
    odesk
    -0.13
    onse
    -0.13
    POSITIVE LOGITS
    ucid
    0.16
     desar
    0.15
    tere
    0.15
    -up
    0.15
    ieve
    0.14
    acre
    0.14
    大åħ¨
    0.14
     ÙĪÙģÙĤ
    0.14
    buz
    0.14
    lém
    0.14
    Act Density 0.013%

    No Known Activations