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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and questions within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barrett
    -0.17
    angelo
    -0.17
    ism
    -0.14
    izable
    -0.14
     Trick
    -0.14
    ilda
    -0.14
     Greenwich
    -0.14
    ochen
    -0.14
     Lucky
    -0.14
    une
    -0.14
    POSITIVE LOGITS
    Decoration
    0.17
    apy
    0.15
    MSN
    0.14
    CSV
    0.14
    ARA
    0.14
    æ³¥
    0.14
    ulur
    0.13
    obel
    0.13
    оÑĤÑĥ
    0.13
    ÐĶÐļ
    0.13
    Act Density 0.053%

    No Known Activations