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

    Neuronpedia

    INDEX
    Explanations

    ratios or fractions in numerical formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rench
    -0.15
    sdale
    -0.15
     Matter
    -0.15
    Ñī
    -0.15
     half
    -0.14
    ackage
    -0.14
    ·
    -0.14
     Suche
    -0.14
     HALF
    -0.14
    aycast
    -0.14
    POSITIVE LOGITS
    FirstChild
    0.15
    iola
    0.15
     THIRD
    0.15
    ãĥ¬ãĥ¼
    0.14
    úde
    0.14
    rax
    0.14
    aggi
    0.14
    ÏĪη
    0.14
    rts
    0.14
    bu
    0.14
    Act Density 0.019%

    No Known Activations