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

    Neuronpedia

    INDEX
    Explanations

    references to law enforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.69
     ſmall
    -0.57
    ̀
    -0.55
    etyl
    -0.54
    czaj
    -0.53
    __":
    -0.53
     Baltic
    -0.52
    ++){
    -0.52
    atilde
    -0.52
     AssemblyVersion
    -0.51
    POSITIVE LOGITS
     whilst
    0.95
     unless
    0.93
     except
    0.93
     while
    0.90
     enquanto
    0.85
     despite
    0.83
     mientras
    0.83
     whereas
    0.81
     kecuali
    0.77
    mientras
    0.75
    Act Density 0.126%

    No Known Activations