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

    Neuronpedia

    INDEX
    Explanations

    phrases that express certainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    velope
    -0.16
    lor
    -0.15
    ÑĢоÑĪ
    -0.15
     Mood
    -0.15
    alis
    -0.15
    trace
    -0.14
     infinity
    -0.14
     Mang
    -0.14
    idy
    -0.14
    ABLE
    -0.14
    POSITIVE LOGITS
    ãĥ©ãĤ¹
    0.15
    12
    0.14
    513
    0.14
    ume
    0.13
    utow
    0.13
    Ñģли
    0.13
    PRODUCT
    0.13
    ieber
    0.13
    329
    0.13
    urch
    0.13
    Act Density 0.028%

    No Known Activations