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

    Neuronpedia

    INDEX
    Explanations

    references to killing or causing death

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     quæ
    -0.74
    arca
    -0.73
     Manus
    -0.72
     terminer
    -0.72
     Sycamore
    -0.69
     izvē
    -0.68
    umumkan
    -0.68
     varandra
    -0.68
    ῇ
    -0.68
     Faro
    -0.67
    POSITIVE LOGITS
     KILL
    0.88
     Kill
    0.84
     kil
    0.83
    FilterChain
    0.83
    KILL
    0.77
     Kil
    0.76
     Kull
    0.75
     kills
    0.73
    UnusedPrivate
    0.73
    kill
    0.72
    Act Density 0.013%

    No Known Activations