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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "ent" and references to line numbers in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tring
    -0.17
     backbone
    -0.16
    ch
    -0.15
    raq
    -0.14
    ub
    -0.14
    uer
    -0.14
    gui
    -0.14
    vg
    -0.14
    ver
    -0.14
     ke
    -0.14
    POSITIVE LOGITS
    antry
    0.17
    пон
    0.16
    ernel
    0.16
    Äįan
    0.15
    aks
    0.15
    tip
    0.14
    άÏģ
    0.14
    isti
    0.14
    ertest
    0.14
    âĢĮÙĨ
    0.14
    Act Density 0.034%

    No Known Activations