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

    Neuronpedia

    INDEX
    Explanations

    terms related to physical and metaphorical injuries, as well as processes of winding or turning, often with a focus on the word "wind"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.15
    arend
    -0.15
    hoo
    -0.15
    conomy
    -0.14
    _contents
    -0.14
    apeut
    -0.14
    ovah
    -0.14
    å±¥
    -0.13
    923
    -0.13
    senal
    -0.13
    POSITIVE LOGITS
     wind
    0.22
    mill
    0.21
    wind
    0.21
    Wind
    0.19
     Wind
    0.19
    -down
    0.16
    erland
    0.16
     gust
    0.16
    .wind
    0.16
    breaker
    0.15
    Act Density 0.008%

    No Known Activations