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

    Neuronpedia

    INDEX
    Explanations

    references to legal proceedings and sentences related to crimes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FAVOR
    -0.98
     vapors
    -0.97
     labors
    -0.91
     FAVOR
    -0.86
     Neighbors
    -0.85
     Traveling
    -0.84
    HEAST
    -0.82
     favorite
    -0.82
     FAVORITE
    -0.81
    AVOR
    -0.80
    POSITIVE LOGITS
    initialise
    1.08
     Gauteng
    0.96
     Pretoria
    0.93
     Initialise
    0.87
     Afrikaans
    0.86
    coloured
    0.85
     Johannesburg
    0.85
     realises
    0.84
     Coloured
    0.83
     realise
    0.83
    Act Density 0.260%

    No Known Activations