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

    Neuronpedia

    INDEX
    Explanations

    references to laundry activities

    oai_token-act-pair · gpt-3.5-turbo

    references to laundry and laundry-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.81
    olar
    -0.76
    pps
    -0.72
    alez
    -0.70
    nels
    -0.70
    hips
    -0.69
    eds
    -0.68
    pg
    -0.67
    ulhu
    -0.67
    oid
    -0.66
    POSITIVE LOGITS
     laundry
    1.24
    ©¶æ¥µ
    0.95
     laund
    0.77
    æ©Ł
    0.76
     closet
    0.75
    å¿
    0.73
    stairs
    0.70
    ãĤ¦ãĤ¹
    0.70
    åĤ
    0.69
     soap
    0.68
    Act Density 0.010%

    No Known Activations