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

    Neuronpedia

    INDEX
    Explanations

    the word "ever."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GenerationType
    -0.84
    stdc
    -0.81
     againſt
    -0.79
     Racine
    -0.79
     fibrillation
    -0.77
     AssemblyTitle
    -0.76
     PBT
    -0.76
    )|^{
    -0.75
    кономі
    -0.75
     Lilli
    -0.75
    POSITIVE LOGITS
     EVER
    1.25
     ever
    1.21
     Ever
    1.17
    ever
    1.13
    Ever
    1.06
    NEVER
    1.05
     never
    1.04
    EVER
    0.96
    ver
    0.96
     NEVER
    0.95
    Act Density 0.008%

    No Known Activations