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

    Neuronpedia

    INDEX
    Explanations

    Specific people, places, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to personal hardships, societal issues, and cultural commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hovah
    -0.66
     oneself
    -0.62
    anwhile
    -0.60
    oward
    -0.55
     Lerner
    -0.54
    rarily
    -0.52
     Canaver
    -0.51
    vae
    -0.51
     Kov
    -0.51
     Azerb
    -0.51
    POSITIVE LOGITS
     counterparts
    0.94
     brethren
    0.83
     counterpart
    0.81
     arsenal
    0.72
     buddies
    0.71
    iest
    0.69
    mates
    0.67
     holdings
    0.66
     woes
    0.65
     cousins
    0.65
    Act Density 0.697%

    No Known Activations