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

    Neuronpedia

    INDEX
    Explanations

    repeated references to the term "plot" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "plot" and associated file paths

    np_acts-logits-general · gemini-2.0-flash

    graphs and plots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.59
    qtype
    -0.55
     McCar
    -0.55
    cyklopedia
    -0.54
     McCarthy
    -0.54
    keits
    -0.53
    iour
    -0.53
    ه
    -0.52
     poter
    -0.51
    rdr
    -0.51
    POSITIVE LOGITS
     Plots
    0.91
     plots
    0.81
     PLOT
    0.78
    Plots
    0.70
    Сюжет
    0.69
    PLOT
    0.69
     Plo
    0.69
     Plot
    0.66
     nonatomic
    0.65
    plots
    0.63
    Act Density 0.120%

    No Known Activations