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

    Neuronpedia

    INDEX
    Explanations

    phrases related to using or applying a brush

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "brush" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.69
     Founding
    -0.68
     regress
    -0.67
    igmat
    -0.66
    rophe
    -0.64
    alg
    -0.64
    ZI
    -0.64
    infeld
    -0.62
    Sax
    -0.62
    uras
    -0.61
    POSITIVE LOGITS
    brush
    1.07
     brush
    0.92
    stroke
    0.89
     strokes
    0.87
     brushes
    0.86
     Brush
    0.85
    tip
    0.83
     brist
    0.83
    stro
    0.82
    asso
    0.80
    Act Density 0.039%

    No Known Activations