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

    Neuronpedia

    INDEX
    Explanations

    references to the term "horizon."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erman
    -0.20
    een
    -0.20
    tle
    -0.19
    ermen
    -0.18
    eenth
    -0.18
    holm
    -0.17
    dom
    -0.17
    nik
    -0.16
    drawing
    -0.16
    ÙħاÙĨÛĮ
    -0.16
    POSITIVE LOGITS
    izons
    0.24
    izont
    0.22
    ìŀ¡
    0.21
    izon
    0.19
    /back
    0.18
    arium
    0.18
    izontally
    0.17
    izontal
    0.17
    iginal
    0.16
    line
    0.16
    Act Density 0.013%

    No Known Activations