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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate frequency or occurrence of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.49
    quete
    -0.48
    uarie
    -0.46
     ales
    -0.44
    Disliked
    -0.44
    findpost
    -0.42
     învă
    -0.42
    ั่ง
    -0.42
    ("]");
    -0.41
    droj
    -0.41
    POSITIVE LOGITS
    writeFieldEnd
    0.99
     everytime
    0.94
     whenever
    0.90
    whenever
    0.85
     Whenever
    0.83
     every
    0.83
    Whenever
    0.82
    every
    0.79
    Every
    0.71
    EVERY
    0.69
    Act Density 0.208%

    No Known Activations