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

    Neuronpedia

    INDEX
    Explanations

    verbs that describe actions or states

    oai_token-act-pair · gpt-3.5-turbo

    verbs suggesting explanations or descriptions of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    selves
    -0.82
     selves
    -0.66
    FL
    -0.62
    mint
    -0.61
    Copyright
    -0.61
     millenn
    -0.59
    illion
    -0.58
    halla
    -0.58
    aroo
    -0.57
    istani
    -0.57
    POSITIVE LOGITS
     herself
    1.21
     himself
    1.07
     her
    0.87
     his
    0.87
     Himself
    0.85
     hers
    0.79
     Chess
    0.60
    âĦ¢:
    0.60
    his
    0.59
     Boh
    0.58
    Act Density 0.474%

    No Known Activations