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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or references to years and centuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     оÑģÑĤан
    -0.15
    eya
    -0.14
    ddit
    -0.14
    åµ
    -0.14
    nesc
    -0.13
    reate
    -0.13
     Ù¾ÙĬ
    -0.13
    饰
    -0.13
    飾
    -0.13
    vere
    -0.13
    POSITIVE LOGITS
    airo
    0.18
    radu
    0.15
     nam
    0.15
    ãĥ¼ãĥķ
    0.14
     augmentation
    0.14
    ->___
    0.14
     >č↵
    0.14
     ofs
    0.14
    olest
    0.13
     arsch
    0.13
    Act Density 0.000%

    No Known Activations