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

    Neuronpedia

    INDEX
    Explanations

    locations or places

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the location of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uploads
    -0.65
    show
    -0.63
    sen
    -0.61
    sequence
    -0.60
    ese
    -0.59
    ework
    -0.59
    doms
    -0.58
     diapers
    -0.57
    spir
    -0.56
    shows
    -0.56
    POSITIVE LOGITS
     atop
    1.08
     near
    1.07
    uate
    1.01
     smack
    0.98
     centrally
    0.97
     northwest
    0.96
     somewhere
    0.96
     southwest
    0.95
     adjacent
    0.95
     northeast
    0.94
    Act Density 0.063%

    No Known Activations