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

    Neuronpedia

    INDEX
    Explanations

    references to economic incentives and the discrepancies in reported figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wilkinson
    -0.15
     شر
    -0.15
    bette
    -0.15
    .newBuilder
    -0.14
    borg
    -0.14
    leftright
    -0.13
    inki
    -0.13
    theon
    -0.13
     mocker
    -0.13
    itter
    -0.13
    POSITIVE LOGITS
     over
    0.39
     overst
    0.36
     underst
    0.34
    Over
    0.33
     Over
    0.32
     OVER
    0.32
    è¿ĩ
    0.32
     unders
    0.31
     inflate
    0.30
     overs
    0.30
    Act Density 0.191%

    No Known Activations