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

    Neuronpedia

    INDEX
    Explanations

    terms related to assassination and its variants

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    henko
    -0.81
     Vogel
    -0.79
    chaik
    -0.79
     Clio
    -0.74
    öf
    -0.72
    بوابة
    -0.70
    gements
    -0.69
     Nel
    -0.69
     flowered
    -0.69
    chaikovsky
    -0.68
    POSITIVE LOGITS
    Ass
    1.69
     Ass
    1.67
    ass
    1.59
     ASS
    1.55
     ass
    1.48
    ASS
    1.44
     Assy
    1.01
     Assassin
    1.01
    Assassin
    0.98
     asses
    0.98
    Act Density 0.016%

    No Known Activations