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

    Neuronpedia

    INDEX
    Explanations

    verbs expressing attribution or categorization

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or statements made about people and their opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maxwell
    -0.64
     Shock
    -0.59
     Revival
    -0.57
     reactive
    -0.57
     ceasefire
    -0.57
     Zeit
    -0.57
     DPR
    -0.56
     Axel
    -0.56
     sts
    -0.55
    resy
    -0.55
    POSITIVE LOGITS
    course
    0.81
     dearly
    0.78
    abouts
    0.73
     deems
    0.70
     deem
    0.68
    unes
    0.68
     cherish
    0.67
    ãĥ¼ãĤ¯
    0.65
    ģĸ
    0.64
    968
    0.64
    Act Density 0.443%

    No Known Activations