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

    Neuronpedia

    INDEX
    Explanations

    non-standard or empty characters in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĮĽ
    -0.15
    073
    -0.15
    emento
    -0.14
    itr
    -0.14
    дал
    -0.14
    uelle
    -0.14
    лива
    -0.14
    lessly
    -0.14
    ught
    -0.14
    ienes
    -0.14
    POSITIVE LOGITS
    erek
    0.18
    è´¨
    0.16
    za
    0.16
    n
    0.15
    fly
    0.15
     Fly
    0.15
    ropolis
    0.14
    zza
    0.14
    mw
    0.14
     Harrison
    0.14
    Act Density 0.010%

    No Known Activations