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

    Neuronpedia

    INDEX
    Explanations

    words related to academic, research, and organizational activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of events or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mpire
    -0.62
    ãģĨ
    -0.61
    76561
    -0.61
     inflamm
    -0.61
    hire
    -0.60
    vation
    -0.60
    death
    -0.58
    ãĤ¤ãĥĪ
    -0.57
    ween
    -0.56
    ascar
    -0.55
    POSITIVE LOGITS
     emphasizes
    0.78
     concludes
    0.78
     encourages
    0.72
     comprises
    0.72
     culmin
    0.72
     illustrates
    0.71
     introduces
    0.70
     demonstrates
    0.70
     consists
    0.70
     aims
    0.70
    Act Density 0.640%

    No Known Activations