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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the action of using a brush

    oai_token-act-pair · gpt-3.5-turbo

    references to brushes and brushing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reme
    -0.77
    uras
    -0.68
     Defenders
    -0.64
    ZI
    -0.63
     Founding
    -0.62
     covenant
    -0.62
    RAL
    -0.62
    oppable
    -0.62
    Sax
    -0.61
    rophe
    -0.61
    POSITIVE LOGITS
    brush
    1.07
     brush
    0.93
     strokes
    0.91
    stroke
    0.90
     Brush
    0.90
    asso
    0.85
     brushes
    0.84
     brist
    0.84
    tip
    0.82
    heet
    0.82
    Act Density 0.035%

    No Known Activations