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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations and travel

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    worthiness
    -0.68
     Nielsen
    -0.67
     Accuracy
    -0.63
     consistency
    -0.61
    gey
    -0.60
     durability
    -0.59
     fact
    -0.57
     extant
    -0.57
     GPL
    -0.57
    utm
    -0.57
    POSITIVE LOGITS
     unnoticed
    0.96
     unaccompanied
    0.96
     undet
    0.92
     smelling
    0.86
     expecting
    0.83
     refuel
    0.83
     whence
    0.83
     escorted
    0.82
     lookout
    0.79
     greet
    0.79
    Act Density 7.135%

    No Known Activations