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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ng
    -0.17
    et
    -0.17
    etta
    -0.16
    eck
    -0.15
    led
    -0.15
    564
    -0.15
     convenience
    -0.15
    -0.15
    tr
    -0.15
    anan
    -0.15
    POSITIVE LOGITS
    ãĥ«ãĥĪ
    0.19
    /*č↵
    0.17
    ÐĶÐļ
    0.16
    ÐŁÐļ
    0.16
    UNUSED
    0.16
    oreach
    0.15
    enderit
    0.15
    ntag
    0.15
    견
    0.15
    _skin
    0.15
    Act Density 0.096%

    No Known Activations