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

    Neuronpedia

    INDEX
    Explanations

    computer code placeholders indicated by special characters like Ċ

    oai_token-act-pair · gpt-3.5-turbo

    references to ratings or evaluations of items and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     camp
    -0.79
     mull
    -0.75
     retard
    -0.75
     Mub
    -0.72
     fleeing
    -0.71
     sculpt
    -0.70
     liber
    -0.69
     ramp
    -0.68
     grop
    -0.68
     ones
    -0.68
    POSITIVE LOGITS
    RAW
    1.80
    Loading
    1.69
    Topic
    1.33
    Reviewer
    1.32
    Introduction
    1.32
    Advertisements
    1.31
    {"
    1.29
    âķIJâķIJ
    1.26
    Discussion
    1.26
    Output
    1.25
    Act Density 0.279%

    No Known Activations