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

    Neuronpedia

    INDEX
    Explanations

    instances of parentheses

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

    speaker attribution in parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.46
    <bos>
    -0.42
     houſe
    -0.41
     ſtate
    -0.40
     pleaſure
    -0.40
     ſtre
    -0.38
    nrow
    -0.37
    !
    -0.37
     ſta
    -0.37
    toEqual
    -0.36
    POSITIVE LOGITS
    （
    1.24
     （
    1.09
    ”（
    1.01
    ）（
    0.98
    ：（
    0.94
    　（
    0.91
    ？（
    0.90
    　　（
    0.90
    」（
    0.88
    。（
    0.85
    Act Density 0.003%

    No Known Activations