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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with ratings or rankings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ^(@)
    -0.96
     myſelf
    -0.95
     itſelf
    -0.93
     photolibrary
    -0.93
     Shakspeare
    -0.91
     Theſe
    -0.91
     Efq
    -0.90
     CreateTagHelper
    -0.90
     Jefus
    -0.88
    ſelves
    -0.88
    POSITIVE LOGITS
     even
    0.54
     Se
    0.52
     rest
    0.51
     Har
    0.50
     re
    0.48
     (
    0.47
     plan
    0.47
    ↵↵
    0.47
     Ter
    0.47
     real
    0.47
    Act Density 0.005%

    No Known Activations