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

    Neuronpedia

    INDEX
    Explanations

    issues related to personal rights, heritage, and cultural identity

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     oneself
    -1.03
     yourselves
    -0.67
    aples
    -0.66
     ourselves
    -0.66
     myself
    -0.62
     extrad
    -0.62
    orks
    -0.61
     Kov
    -0.61
     yourself
    -0.61
     Yourself
    -0.60
    POSITIVE LOGITS
     counterparts
    1.29
     selves
    1.18
     counterpart
    1.13
     brethren
    1.09
    mates
    0.99
     holdings
    0.96
     woes
    0.95
     predecessors
    0.95
    mate
    0.93
     arsenal
    0.93
    Act Density 4.255%

    No Known Activations