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

    Neuronpedia

    INDEX
    Explanations

    negative or positive evaluations and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    $LANG
    -0.18
    .BorderFactory
    -0.18
    /Dk
    -0.15
    ¶Į
    -0.15
    OUNCE
    -0.15
     Hüs
    -0.15
     èĩªåĬ¨çĶŁæĪIJ
    -0.15
    SupportedContent
    -0.15
    .scalablytyped
    -0.14
    luet
    -0.14
    POSITIVE LOGITS
    -that
    0.20
    -of
    0.20
    -with
    0.20
    2
    0.19
    -between
    0.19
    -this
    0.19
    -for
    0.18
    -to
    0.18
    1
    0.18
    -on
    0.17
    Act Density 0.206%

    No Known Activations