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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word "we"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.87
    rungsseite
    -0.84
    Datuak
    -0.80
     ModelExpression
    -0.74
     kasarigan
    -0.68
     Вікі
    -0.67
    ISupport
    -0.67
    StoryboardSegue
    -0.65
    längerung
    -0.63
     nakalista
    -0.61
    POSITIVE LOGITS
    we
    2.38
    WE
    2.35
     WE
    1.69
    wea
    1.01
    they
    0.99
    weg
    0.87
    THEY
    0.86
    wes
    0.85
    wee
    0.83
    web
    0.81
    Act Density 0.063%

    No Known Activations