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

    Neuronpedia

    INDEX
    Explanations

    references to formal structures and variables in equations or scientific discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plex
    -0.16
     inters
    -0.15
    erp
    -0.14
    okoj
    -0.14
    637
    -0.14
    ÑĥÑĢÑģ
    -0.14
    áºł
    -0.14
     gut
    -0.14
    edic
    -0.13
    isen
    -0.13
    POSITIVE LOGITS
    Loop
    0.19
     loop
    0.19
     Sud
    0.18
     Loop
    0.18
    -loop
    0.18
    jets
    0.18
    jet
    0.18
    loop
    0.18
    ducible
    0.17
     jet
    0.17
    Act Density 0.007%

    No Known Activations