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

    Neuronpedia

    INDEX
    Explanations

    phrases related to locker rooms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     philips
    -0.83
     effe
    -0.81
     intermitt
    -0.78
     ?...
    -0.77
     gild
    -0.77
     eyel
    -0.76
     fuf
    -0.76
     scrat
    -0.76
     helico
    -0.75
     ugg
    -0.74
    POSITIVE LOGITS
     locker
    1.33
     lockers
    1.00
    locker
    0.88
     Locker
    0.83
    Locker
    0.78
     lock
    0.57
     dressing
    0.57
     closet
    0.54
     wardrobe
    0.53
    زندگی
    0.52
    Act Density 0.094%

    No Known Activations