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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and notation related to partitions and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fjspx
    -0.71
    はじめに
    -0.68
     Exactos
    -0.67
     nakalista
    -0.67
    Datuak
    -0.66
     Himo
    -0.65
    )++;
    -0.65
    хьтан
    -0.64
     Infórmanos
    -0.63
     annuelle
    -0.62
    POSITIVE LOGITS
    bar
    0.96
     bar
    0.93
    Bar
    0.85
     Bar
    0.85
     BAR
    0.74
     bars
    0.69
    бар
    0.68
    BAR
    0.68
    IBar
    0.67
     fever
    0.63
    Act Density 2.662%

    No Known Activations