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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "over-" as a prefix in various contexts

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

    over-expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſich
    -0.63
     feroit
    -0.62
     plufieurs
    -0.62
     laſſen
    -0.61
     sekal
    -0.61
     ſeinen
    -0.59
     müſſen
    -0.59
     Geiſt
    -0.59
     increí
    -0.58
     CreateTagHelper
    -0.58
    POSITIVE LOGITS
    TestingModule
    0.51
    $_['
    0.42
    subpackage
    0.42
    -
    0.42
     (
    0.42
    _
    0.41
    ::_('
    0.37
    FunctionFlags
    0.37
    <sub>
    0.36
     -
    0.35
    Act Density 0.014%

    No Known Activations