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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of violence in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jang
    -0.76
    ennett
    -0.71
    ggable
    -0.69
    *}[
    -0.69
    eable
    -0.69
    tanks
    -0.68
     @"/
    -0.66
    tank
    -0.64
    Fak
    -0.63
     Constantinople
    -0.62
    POSITIVE LOGITS
     tourism
    0.88
     dataType
    0.86
     useNavigate
    0.84
    ."</
    0.83
    awtextra
    0.79
     LCCN
    0.75
     violence
    0.72
    なりません
    0.72
     OMITTED
    0.72
     Acerca
    0.71
    Act Density 0.121%

    No Known Activations