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

    Neuronpedia

    INDEX
    Explanations

    scientific citations and references in a structured format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Архівовано
    -0.58
     bar
    -0.49
    teig
    -0.49
     cre
    -0.47
    ेंद
    -0.46
     Sol
    -0.45
    ьаж
    -0.45
    COUVER
    -0.43
    ************/
    -0.43
    oire
    -0.42
    POSITIVE LOGITS
     Efq
    0.88
     ujednoznacz
    0.83
    IntoConstraints
    0.82
     Monfieur
    0.79
     myſelf
    0.77
     raiſ
    0.76
     الحره
    0.74
     pleaſure
    0.72
     ſhe
    0.71
     ―――――
    0.71
    Act Density 0.003%

    No Known Activations