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

    Neuronpedia

    INDEX
    Explanations

    names of places and cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "San Francisco" and related abbreviations or variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     favors
    -0.64
    glers
    -0.62
     offset
    -0.61
     deaf
    -0.60
     irregularities
    -0.59
     favor
    -0.59
    ilater
    -0.58
     knitting
    -0.58
     Starr
    -0.57
     stitch
    -0.57
    POSITIVE LOGITS
    士
    0.86
    eus
    0.71
    emy
    0.70
    atra
    0.69
    thia
    0.68
    Gas
    0.67
    ctic
    0.67
    escal
    0.67
    encia
    0.66
    itary
    0.65
    Act Density 0.074%

    No Known Activations