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

    Neuronpedia

    INDEX
    Explanations

    words related to urban development and city planning

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebus
    -0.85
    ricanes
    -0.82
    aido
    -0.80
    anwhile
    -0.79
    acas
    -0.78
    oak
    -0.77
    gres
    -0.76
    glers
    -0.74
    colo
    -0.74
    apor
    -0.73
    POSITIVE LOGITS
     downright
    1.17
     counterproductive
    1.10
     detract
    1.03
     deserves
    1.03
     deserving
    1.02
     punishable
    0.99
     detrimental
    0.99
     unavoidable
    0.99
     understandable
    0.97
     certainly
    0.97
    Act Density 2.436%

    No Known Activations