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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "out" and its usage in different contexts

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

    "out" or its variations

    np_acts-logits-general · gemini-2.0-flash

    out there, out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.89
    Javadoc
    -0.70
    complexContent
    -0.69
     فريبيس
    -0.66
    SequentialGroup
    -0.65
    routeProvider
    -0.63
    SHIPS
    -0.60
    rrer
    -0.60
    etheless
    -0.60
     लिया
    -0.59
    POSITIVE LOGITS
     OUT
    1.00
     Out
    0.86
     out
    0.80
    Out
    0.78
    out
    0.76
    OUT
    0.72
    getOut
    0.66
     loud
    0.64
     []:
    0.64
    pout
    0.63
    Act Density 0.313%

    No Known Activations