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

    Neuronpedia

    INDEX
    Explanations

    references to unknown sources or errors in configuration logs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çı
    -0.16
     podium
    -0.15
    ller
    -0.15
    ugin
    -0.15
    еÑĨÑĤ
    -0.14
    urum
    -0.14
    ych
    -0.14
    arian
    -0.14
    ãĤĤãģĹ
    -0.14
    UGIN
    -0.13
    POSITIVE LOGITS
     Caucus
    0.15
    iry
    0.15
    ije
    0.14
    IRS
    0.14
     ><?
    0.14
    621
    0.14
     cross
    0.14
    UMB
    0.13
    eniable
    0.13
    yes
    0.13
    Act Density 0.023%

    No Known Activations