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

    Neuronpedia

    INDEX
    Explanations

    phrases related to manual actions or skills

    oai_token-act-pair · gpt-3.5-turbo

    references to hand-processed or crafted items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Revenue
    -0.67
    iatus
    -0.66
     adversely
    -0.66
     TT
    -0.65
     sunset
    -0.64
     postp
    -0.64
     Cah
    -0.63
     beta
    -0.62
     limitation
    -0.61
     inconsistencies
    -0.61
    POSITIVE LOGITS
    eye
    1.53
    held
    1.46
    selected
    1.38
    picked
    1.33
    drawn
    1.22
    crafted
    1.17
    painted
    1.17
    washing
    1.16
    worn
    1.15
    holding
    1.14
    Act Density 0.039%

    No Known Activations