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

    Neuronpedia

    INDEX
    Explanations

    technical terms and quantitative data related to models and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.67
     otomatig
    -0.64
     Munch
    -0.63
     TUL
    -0.61
    ·
    -0.59
    jspx
    -0.57
     XL
    -0.57
     TG
    -0.55
     Lal
    -0.55
     Ida
    -0.54
    POSITIVE LOGITS
     Wray
    0.88
     GK
    0.79
     Yunus
    0.71
     Bress
    0.67
     Clegg
    0.66
     Bolton
    0.66
     repository
    0.65
     Adventist
    0.65
     Marne
    0.64
     impedance
    0.64
    Act Density 1.147%

    No Known Activations