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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bourg
    -0.17
    .scalablytyped
    -0.16
     essentially
    -0.16
     probably
    -0.16
     Probably
    -0.15
     basically
    -0.15
     zÅĻejmÄĽ
    -0.15
    rsa
    -0.15
    ardo
    -0.15
     apparently
    -0.15
    POSITIVE LOGITS
     even
    0.45
    even
    0.36
     sogar
    0.32
     Even
    0.30
     даже
    0.29
    Even
    0.29
     slightly
    0.28
     EVEN
    0.26
     навÑĸÑĤÑĮ
    0.26
    çĶļèĩ³
    0.25
    Act Density 0.087%

    No Known Activations