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

    Neuronpedia

    INDEX
    Explanations

    references to the location "Manhattan."

    oai_token-act-pair · gpt-3.5-turbo

    references to Manhattan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ional
    -0.88
    ioned
    -0.82
    ivia
    -0.80
    np
    -0.79
    inen
    -0.79
    utic
    -0.76
    ive
    -0.75
    vo
    -0.74
    fully
    -0.73
    milo
    -0.72
    POSITIVE LOGITS
     borough
    1.19
     Borough
    1.16
     skysc
    0.96
     skyline
    0.94
     Beach
    0.92
     apartment
    0.84
     Projects
    0.83
     subway
    0.83
     Island
    0.79
     Jets
    0.79
    Act Density 0.074%

    No Known Activations