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

    Neuronpedia

    INDEX
    Explanations

    words and phrases associated with winning and competition

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

    Following "the," "win," or "won."

    np_acts-logits-general · gemini-2.0-flash

    winning titles and awards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.85
    BufferException
    -0.84
     SEDS
    -0.79
    contentLoaded
    -0.76
     TestBed
    -0.76
    aarrggbb
    -0.72
    buttonBar
    -0.69
    OrBuilder
    -0.69
     وتسجيلات
    -0.67
    extAlignment
    -0.67
    POSITIVE LOGITS
     title
    0.93
     honors
    0.88
     coveted
    0.82
     laurels
    0.80
     accolades
    0.79
     titles
    0.79
     prizes
    0.79
     honours
    0.77
     prize
    0.76
     bragging
    0.76
    Act Density 0.224%

    No Known Activations