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

    Neuronpedia

    INDEX
    Explanations

    phrases related to items stored in pockets

    oai_token-act-pair · gpt-3.5-turbo

    references to pockets and items associated with them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.85
    mberg
    -0.68
    Reviewer
    -0.66
    abad
    -0.65
    ERO
    -0.64
    actionDate
    -0.64
     Relations
    -0.63
    IAS
    -0.61
    jad
    -0.61
    DEF
    -0.60
    POSITIVE LOGITS
    knife
    1.26
    book
    0.93
    notes
    0.93
    books
    0.86
    watch
    0.84
    tex
    0.83
    roll
    0.80
     knife
    0.79
    pocket
    0.77
    bag
    0.76
    Act Density 0.038%

    No Known Activations