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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expensive items or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to high costs or expense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mbuds
    -0.93
    vironment
    -0.88
    mbudsman
    -0.81
    hirt
    -0.75
    terness
    -0.75
    unin
    -0.72
    İĭ
    -0.71
    ©¶æ
    -0.71
    udeb
    -0.71
    uberty
    -0.71
    POSITIVE LOGITS
    ly
    1.05
    liest
    0.95
     expensive
    0.93
     ($
    0.90
    lier
    0.88
     prohib
    0.80
     extravag
    0.80
     pricey
    0.80
     (£
    0.79
     premiums
    0.79
    Act Density 0.042%

    No Known Activations