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

    Neuronpedia

    INDEX
    Explanations

    references to cats or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     quedo
    -0.33
    AutoScale
    -0.33
     atractivo
    -0.31
     atractivos
    -0.29
     __
    -0.29
    orghe
    -0.28
    awić
    -0.27
     Pública
    -0.27
     Züge
    -0.27
     gustaba
    -0.26
    POSITIVE LOGITS
     Cat
    0.79
     CAT
    0.78
    Cat
    0.76
     meow
    0.75
    Tikang
    0.75
     getCategory
    0.72
     cat
    0.70
     Cata
    0.69
    ollectionView
    0.68
    apult
    0.67
    Act Density 0.148%

    No Known Activations