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

    Neuronpedia

    INDEX
    Explanations

    architectural references or terms

    oai_token-act-pair · gpt-3.5-turbo

    the prefix "ar" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HAEL
    -0.69
    éĹĺ
    -0.68
    ĸļ
    -0.68
    ¬¼
    -0.60
    tons
    -0.60
    ortium
    -0.58
     Prosper
    -0.58
     moderation
    -0.58
    ega
    -0.56
     disproportion
    -0.56
    POSITIVE LOGITS
    ctic
    1.25
    beit
    1.15
    throp
    1.11
    chery
    1.08
    rival
    1.06
    thouse
    1.05
    duino
    1.04
    chers
    1.04
    thur
    1.00
    cher
    0.99
    Act Density 0.011%

    No Known Activations