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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past participle form, often related to actions taken by someone or something

    oai_token-act-pair · gpt-3.5-turbo

    past participles or verbs that suggest completion or action taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utra
    -0.69
    adra
    -0.66
    è£ħ
    -0.65
    Ļ½
    -0.63
    achu
    -0.62
    adier
    -0.62
    hov
    -0.62
    í
    -0.61
    RESULTS
    -0.60
    «ĺ
    -0.60
    POSITIVE LOGITS
    paren
    0.78
    escription
    0.78
    own
    0.78
    rive
    0.76
    river
    0.72
    nesday
    0.72
     subur
    0.71
     BY
    0.70
     aback
    0.70
     murd
    0.70
    Act Density 0.542%

    No Known Activations