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

    occurrences of the word "Manhattan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebook
    -0.82
    ional
    -0.78
    ollow
    -0.75
    vo
    -0.73
    printf
    -0.71
    np
    -0.70
    saf
    -0.70
    ords
    -0.69
    doors
    -0.69
    paying
    -0.68
    POSITIVE LOGITS
     Manhattan
    1.22
     Borough
    0.95
    hattan
    0.93
     borough
    0.88
     skyline
    0.85
     Island
    0.84
     Beach
    0.83
     skysc
    0.83
     Jets
    0.79
     Plaza
    0.78
    Act Density 0.005%

    No Known Activations