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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal claims and accusations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ydable
    -0.50
     presidencial
    -0.47
     esimerkiksi
    -0.47
    Litteratur
    -0.45
     sisält
    -0.43
    seguida
    -0.43
     obuv
    -0.42
     hänen
    -0.41
     ilustracja
    -0.41
     muun
    -0.41
    POSITIVE LOGITS
    
    0.62
    .,
    0.62
    CppMethod
    0.60
     disambiguazione
    0.59
    .;
    0.57
    ฯ
    0.57
    omitempty
    0.56
    ./
    0.54
     BoxFit
    0.53
     ✭✭
    0.52
    Act Density 1.121%

    No Known Activations