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

    Neuronpedia

    INDEX
    Explanations

    negative phrases related to advice or warnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilities
    -0.18
    ickerView
    -0.17
    ual
    -0.15
    iais
    -0.15
    iors
    -0.15
    ustomed
    -0.15
    aoke
    -0.15
    ioned
    -0.15
    amoto
    -0.15
    MMdd
    -0.14
    POSITIVE LOGITS
    ìį¨
    0.15
    Ïģκ
    0.15
    íķĺìĦ¸ìļĶ
    0.15
    ATCH
    0.13
    oya
    0.13
     necessarily
    0.13
    ůj
    0.13
     Simpson
    0.13
    üç
    0.13
    rish
    0.13
    Act Density 0.028%

    No Known Activations