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

    Neuronpedia

    INDEX
    Explanations

    various types of mathematical expressions and symbols, particularly parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.67
    es
    -0.60
    сто
    -0.59
     to
    -0.57
    ing
    -0.56
     from
    -0.54
     for
    -0.54
    ))->
    -0.54
     conven
    -0.52
     ē
    -0.52
    POSITIVE LOGITS
    ">(</
    1.29
    ($(
    1.23
     $_(
    1.13
     ($(
    1.13
     }}(
    1.13
    }(
    1.13
    (\
    1.13
    __(
    1.09
     }^{(
    1.08
    ”(
    1.05
    Act Density 0.246%

    No Known Activations