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

    Neuronpedia

    INDEX
    Explanations

    strong emotional or sensory elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebek
    -0.18
     Gü
    -0.18
    inear
    -0.17
    >manual
    -0.16
     Sunder
    -0.15
    än
    -0.15
    Fourth
    -0.14
    adÃŃ
    -0.14
    ecycle
    -0.14
    ToFit
    -0.14
    POSITIVE LOGITS
    co
    0.19
     Mai
    0.17
     Pace
    0.17
    153
    0.16
    542
    0.15
    coat
    0.15
    IT
    0.15
     Harrison
    0.15
     lakes
    0.15
     Coat
    0.15
    Act Density 0.028%

    No Known Activations