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

    Neuronpedia

    INDEX
    Explanations

    references to sports moments and narratives of underdog victories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ornings
    -0.16
    Ñıд
    -0.15
    inati
    -0.15
    istrovstvÃŃ
    -0.14
    phere
    -0.14
    ields
    -0.14
    killer
    -0.13
     îł
    -0.13
     jadx
    -0.13
    зд
    -0.13
    POSITIVE LOGITS
     upset
    0.44
     Cinder
    0.33
     surprise
    0.31
     David
    0.30
     under
    0.28
     unexpected
    0.27
     dark
    0.26
     Dav
    0.25
     surprises
    0.25
     unlikely
    0.24
    Act Density 0.192%

    No Known Activations