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

    Neuronpedia

    INDEX
    Explanations

    concepts related to creation, modification, and collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÃŃ
    -0.20
    ify
    -0.17
    ìĦł
    -0.17
    ola
    -0.16
    ë¡ľ
    -0.15
    itter
    -0.15
    sik
    -0.15
    ing
    -0.15
    ING
    -0.15
    és
    -0.15
    POSITIVE LOGITS
    ary
    0.38
    naire
    0.36
    ally
    0.35
    naires
    0.29
    als
    0.28
    al
    0.27
    nal
    0.27
    nelle
    0.27
    nel
    0.27
    ist
    0.27
    Act Density 1.682%

    No Known Activations