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

    Neuronpedia

    INDEX
    Explanations

    research-related terms and organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of research institutions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     femin
    -0.62
    icago
    -0.61
    âĶĢâĶĢ
    -0.61
     dism
    -0.61
    conv
    -0.61
     cringe
    -0.60
     crushing
    -0.59
     Rowling
    -0.58
    size
    -0.58
     coincidence
    -0.57
    POSITIVE LOGITS
     Associates
    0.91
     Laboratory
    0.91
     Scientist
    0.87
     Laboratories
    0.87
    hod
    0.83
     Partners
    0.83
     Institute
    0.82
     Digest
    0.81
     Researchers
    0.79
     Analyst
    0.78
    Act Density 0.026%

    No Known Activations