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

    Neuronpedia

    INDEX
    Explanations

    mentions of the term "high" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases starting with High

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -1.00
     Futter
    -0.53
    esercito
    -0.52
    occasione
    -0.50
     unreal
    -0.48
     top
    -0.48
     Petter
    -0.46
    mba
    -0.46
    сторія
    -0.46
     entrepreneurial
    -0.45
    POSITIVE LOGITS
     High
    1.39
    High
    1.27
     HIGH
    0.87
    HIGH
    0.82
     Hohe
    0.63
     Высо
    0.61
     "..\..\..\
    0.60
    的高
    0.57
    Highlight
    0.57
    Low
    0.56
    Act Density 0.011%

    No Known Activations