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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal actions, authority, and social responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and their frequency in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rio
    -0.70
    ãĤ´ãĥ³
    -0.67
    etry
    -0.65
    itiz
    -0.65
    ãĤ©
    -0.65
    ogo
    -0.62
    ety
    -0.62
    ãĥ¢
    -0.60
    tains
    -0.59
    eur
    -0.59
    POSITIVE LOGITS
    their
    1.29
    selves
    1.28
     They
    1.25
     Their
    1.23
    Their
    1.23
    They
    1.21
    they
    1.20
     themselves
    1.16
     THEIR
    1.15
     THEY
    1.15
    Act Density 0.973%

    No Known Activations