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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or processes undertaken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ud
    -0.15
    vert
    -0.14
    oi
    -0.14
    raž
    -0.14
    heim
    -0.14
    ved
    -0.14
    èĶ
    -0.14
    cake
    -0.13
    itta
    -0.13
    HG
    -0.13
    POSITIVE LOGITS
     so
    0.41
    å¦ĤæѤ
    0.23
     ÑĤак
    0.21
    so
    0.20
     So
    0.18
     så
    0.18
     such
    0.18
    So
    0.17
    igin
    0.17
    .so
    0.15
    Act Density 0.037%

    No Known Activations