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

    Neuronpedia

    INDEX
    Explanations

    phrases and expressions indicating affection and enthusiasm for specific shows, ideas, or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .ua
    -0.18
    ieber
    -0.16
    rna
    -0.15
    à¹Ħ
    -0.14
    ernals
    -0.14
    ynam
    -0.14
     usted
    -0.14
    á»ĭ
    -0.14
    readcr
    -0.14
    inski
    -0.13
    POSITIVE LOGITS
     yourself
    0.17
    ko
    0.16
    pong
    0.16
    aket
    0.16
    lette
    0.15
     Hampton
    0.15
    aris
    0.14
    anguage
    0.14
    inez
    0.14
    pras
    0.14
    Act Density 1.390%

    No Known Activations