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

    Neuronpedia

    INDEX
    Explanations

    references to mountains and hilly landscapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DELHI
    -0.79
    irical
    -0.72
    CHICAGO
    -0.69
    vieja
    -0.69
     Qantas
    -0.67
     CHICAGO
    -0.66
    çais
    -0.64
     sanitarios
    -0.64
     hefyd
    -0.64
    fredo
    -0.63
    POSITIVE LOGITS
     hills
    1.55
     mountain
    1.48
     mountains
    1.46
     hill
    1.41
     Mountain
    1.37
    Mountain
    1.27
     Hills
    1.24
     Mountains
    1.21
     Hill
    1.21
    mountain
    1.17
    Act Density 0.120%

    No Known Activations