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

    Neuronpedia

    INDEX
    Explanations

    references to plots and plot analysis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dede
    -0.74
     /\.(
    -0.68
    ReusableCell
    -0.66
    Unmount
    -0.63
     Amon
    -0.62
     ceux
    -0.61
     dzień
    -0.59
     республики
    -0.59
     siglas
    -0.59
    Bien
    -0.59
    POSITIVE LOGITS
     plot
    2.75
     plots
    2.63
    plot
    2.62
     Plot
    2.57
     PLOT
    2.52
     Plots
    2.48
    Plot
    2.39
    PLOT
    2.27
    plots
    2.25
    Plots
    2.11
    Act Density 0.111%

    No Known Activations