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

    Neuronpedia

    INDEX
    Explanations

    references to new developments or transformations across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     backgrounds
    -0.18
     background
    -0.15
     BACKGROUND
    -0.14
     Background
    -0.14
    amage
    -0.14
    rng
    -0.13
     countries
    -0.13
    æĢ§çļĦ
    -0.13
    peech
    -0.13
    urette
    -0.13
    POSITIVE LOGITS
     breed
    0.40
     era
    0.38
     wave
    0.33
     Breed
    0.30
    -era
    0.27
    -wave
    0.27
     Era
    0.27
     generation
    0.27
     chapter
    0.27
     dawn
    0.27
    Act Density 0.083%

    No Known Activations