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

    Neuronpedia

    INDEX
    Explanations

    verbs related to progress and action

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate actions or changes made by a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toggle
    -0.71
    picture
    -0.70
    gery
    -0.69
     Dying
    -0.66
    fter
    -0.66
    clip
    -0.65
    ggles
    -0.63
     CARE
    -0.62
    ctions
    -0.62
    ADVERTISEMENT
    -0.62
    POSITIVE LOGITS
     raining
    0.79
     incre
    0.74
     costs
    0.73
    rodu
    0.68
    ueller
    0.66
     imperative
    0.64
     easier
    0.63
    endix
    0.61
     cheaper
    0.61
     predecessor
    0.61
    Act Density 0.638%

    No Known Activations