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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to coding and databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     וב
    -0.42
     כשה
    -0.39
     anschließend
    -0.38
     מל
    -0.38
    عتبر
    -0.36
    wendungs
    -0.35
     afterward
    -0.35
     deles
    -0.35
     وك
    -0.35
     suom
    -0.34
    POSITIVE LOGITS
     queſta
    0.89
    __(/*!
    0.80
    niſſe
    0.77
    iſchen
    0.76
    ⦑
    0.73
    <pad>
    0.70
     ſans
    0.70
    <unused28>
    0.70
    <unused20>
    0.70
    <unused17>
    0.70
    Act Density 1.749%

    No Known Activations