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

    Neuronpedia

    INDEX
    Explanations

    phrases and terms denoting examples or instances in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CURLOPT
    -0.72
    ỏi
    -0.65
    日在
    -0.65
    وردار
    -0.64
    히
    -0.62
     demais
    -0.60
     divisa
    -0.60
     '',
    -0.59
     >=",
    -0.59
    ertia
    -0.59
    POSITIVE LOGITS
     examples
    1.71
    examples
    1.58
     example
    1.52
    ByExample
    1.48
    example
    1.42
     Examples
    1.41
     EXAMPLE
    1.40
    Example
    1.37
    Examples
    1.36
     Example
    1.34
    Act Density 0.086%

    No Known Activations