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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pop
    -0.66
    rep
    -0.66
    pun
    -0.63
     frig
    -0.63
    Zip
    -0.61
     penal
    -0.60
    Tag
    -0.60
    sit
    -0.60
    ãĥ¬
    -0.58
    Pur
    -0.58
    POSITIVE LOGITS
    pez
    0.75
    },"
    0.73
     therein
    0.68
    thren
    0.68
    Interstitial
    0.67
    iasco
    0.67
    ndum
    0.67
    OTUS
    0.66
    aukee
    0.62
    oji
    0.62
    Act Density 0.147%

    No Known Activations