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

    Neuronpedia

    INDEX
    Explanations

    technical terms and information related to computer science, particularly in the context of research papers, product reviews, and software development

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     salute
    -0.73
     Buc
    -0.69
    ript
    -0.68
     Voting
    -0.65
     Tate
    -0.63
     Volunteers
    -0.62
    udos
    -0.61
     statue
    -0.61
     Zel
    -0.61
    minus
    -0.61
    POSITIVE LOGITS
     situations
    0.92
     browsing
    0.81
     emergencies
    0.80
     allergies
    0.79
     allergic
    0.74
     allergy
    0.72
     applications
    0.71
     environments
    0.71
     sensitive
    0.71
     ingest
    0.71
    Act Density 4.819%

    No Known Activations