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

    Neuronpedia

    INDEX
    Explanations

    references to individuals' thoughts, beliefs, and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eld
    -0.16
    reich
    -0.16
    zbek
    -0.15
    fahren
    -0.14
    ÙĩرÙĩ
    -0.14
    xCD
    -0.14
    apiro
    -0.13
    aver
    -0.13
    iran
    -0.13
    nie
    -0.13
    POSITIVE LOGITS
    holm
    0.16
    375
    0.15
    hone
    0.15
    etur
    0.15
    uten
    0.15
    iber
    0.14
     Sor
    0.14
    ycz
    0.14
    ettle
    0.14
    iyon
    0.14
    Act Density 0.217%

    No Known Activations