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

    Neuronpedia

    INDEX
    Explanations

    references to items related to pockets

    oai_token-act-pair · gpt-3.5-turbo

    references to pockets or things that can be carried in pockets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.99
    Reviewer
    -0.78
    ————————————————
    -0.74
    rd
    -0.71
    actionDate
    -0.69
    EMENT
    -0.66
    SPA
    -0.66
     Cosponsors
    -0.64
     Relations
    -0.64
     Victims
    -0.64
    POSITIVE LOGITS
    knife
    1.08
    book
    0.92
    pocket
    0.91
    books
    0.90
    wallet
    0.90
     pocket
    0.85
    notes
    0.85
    ipes
    0.81
    clip
    0.81
    tex
    0.78
    Act Density 0.028%

    No Known Activations