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

    Neuronpedia

    INDEX
    Explanations

    repeated occurrences of the word "smart" or its variations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -1.13
     AssemblyTitle
    -1.05
    ^(@)
    -0.91
     écl
    -0.89
    ThemeOverlay
    -0.84
     Scrolls
    -0.81
    ]{\
    -0.80
     Palette
    -0.78
    TabIndex
    -0.77
    islation
    -0.77
    POSITIVE LOGITS
    mart
    0.73
    3
    0.73
    2
    0.71
    <strong>
    0.68
     Smart
    0.65
    ward
    0.64
    1
    0.63
    art
    0.63
    жи
    0.63
    smart
    0.63
    Act Density 0.002%

    No Known Activations