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

    Neuronpedia

    INDEX
    Explanations

    verbs related to sudden, sharp, or unexpected actions or changes

    oai_token-act-pair · gpt-3.5-turbo

    action-related verbs indicating significant change or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     design
    -0.69
     support
    -0.68
     link
    -0.68
     launch
    -0.67
     purchase
    -0.66
     release
    -0.66
     protest
    -0.66
     sanction
    -0.66
     invent
    -0.63
     review
    -0.63
    POSITIVE LOGITS
     swapped
    1.91
     flipped
    1.90
     pounded
    1.86
     dumped
    1.85
     tossed
    1.81
     clicked
    1.80
     emptied
    1.77
     rubbed
    1.76
     slashed
    1.75
     sucked
    1.73
    Act Density 0.103%

    No Known Activations