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

    Neuronpedia

    INDEX
    Explanations

    terms related to storing or hoarding items

    oai_token-act-pair · gpt-3.5-turbo

    terms related to stockpiling and storing resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adv
    -0.73
    obo
    -0.69
    ctory
    -0.65
    hood
    -0.65
    win
    -0.64
     Independent
    -0.64
    nor
    -0.63
     Reson
    -0.63
     Pall
    -0.63
    yon
    -0.62
    POSITIVE LOGITS
     stockp
    1.27
     stockpile
    1.24
    ãĥ¼ãĥĨãĤ£
    1.03
     stash
    0.97
    ickr
    0.92
     holdings
    0.91
    itures
    0.88
     depot
    0.81
     hoard
    0.80
    apons
    0.79
    Act Density 0.009%

    No Known Activations