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

    Neuronpedia

    INDEX
    Explanations

    language-related terms and code syntax in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.02
     ་་
    -0.91
     ―――――
    -0.86
    ^(@)
    -0.85
     photolibrary
    -0.84
     $_"
    -0.84
    }%
    -0.83
     myſelf
    -0.82
     (\<
    -0.82
    \<^
    -0.82
    POSITIVE LOGITS
    yarnpkg
    0.54
     Polskiego
    0.53
    -
    0.53
    &
    0.52
    !
    0.49
     versão
    0.49
    Entry
    0.49
     _
    0.48
    にあ
    0.48
    <strong>
    0.48
    Act Density 0.375%

    No Known Activations