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

    Neuronpedia

    INDEX
    Explanations

    references to hills or elevated landforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    textbf
    -0.75
    toMatchSnapshot
    -0.72
     Knockout
    -0.71
    emias
    -0.70
    gnac
    -0.69
     Breda
    -0.69
    sé
    -0.68
     gefü
    -0.67
     Herrmann
    -0.66
    Quo
    -0.66
    POSITIVE LOGITS
     Hill
    2.05
     hill
    1.96
    Hill
    1.95
     HILL
    1.89
     hills
    1.78
    hill
    1.70
     Hills
    1.59
    HILL
    1.54
    Hills
    1.34
     HILLS
    1.31
    Act Density 0.055%

    No Known Activations