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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or behaviors carried out by people

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or experiences related to decision-making or public sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ü
    -0.60
     Everything
    -0.60
     Roundup
    -0.60
     Adventures
    -0.60
     Quarter
    -0.59
    ãĤ´
    -0.59
     Athletics
    -0.59
     Buster
    -0.59
     sorts
    -0.58
     Guys
    -0.58
    POSITIVE LOGITS
    Reviewed
    0.73
    nai
    0.71
    rake
    0.70
    ometric
    0.68
    iw
    0.67
    wolves
    0.67
    horn
    0.66
     outright
    0.66
    seys
    0.66
    pees
    0.66
    Act Density 0.227%

    No Known Activations