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

    Neuronpedia

    INDEX
    Explanations

    different mentions involving pockets or pocket-related activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.88
    abad
    -0.83
    Reviewer
    -0.77
    rd
    -0.75
    ————————————————
    -0.67
    xual
    -0.67
    slow
    -0.63
    udic
    -0.61
    ERO
    -0.60
    ivia
    -0.59
    POSITIVE LOGITS
    books
    0.87
    pocket
    0.87
    knife
    0.84
    book
    0.84
    wallet
    0.84
    notes
    0.77
     pocket
    0.76
    ably
    0.74
    watch
    0.74
    tex
    0.72
    Act Density 0.689%

    No Known Activations