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

    Neuronpedia

    INDEX
    Explanations

    references to pockets, particularly in a metaphorical sense

    oai_token-act-pair · gpt-3.5-turbo

    references to metaphorical or literal pockets, often relating to wealth or money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.89
     Relations
    -0.68
    =-=-=-=-
    -0.68
     Abuse
    -0.65
    ctive
    -0.64
    Scient
    -0.64
    SHIP
    -0.63
    ————————————————
    -0.61
     Orth
    -0.61
    Cond
    -0.61
    POSITIVE LOGITS
    pocket
    1.08
     pocket
    1.05
     pockets
    1.04
    pak
    0.81
    ensibly
    0.80
     pouch
    0.80
    robe
    0.79
    ython
    0.78
    acking
    0.78
    nuts
    0.77
    Act Density 0.006%

    No Known Activations