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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to organizational structure or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orte
    -0.15
    aston
    -0.14
    ihil
    -0.14
    emez
    -0.13
    ibal
    -0.13
     ki
    -0.13
     dub
    -0.13
    phys
    -0.13
    MAND
    -0.12
    licit
    -0.12
    POSITIVE LOGITS
    pri
    0.16
    uffix
    0.14
     PRI
    0.13
    btc
    0.13
     Wagner
    0.13
    âĢIJ
    0.13
    PRI
    0.12
    DebugEnabled
    0.12
    æ°ı
    0.12
    umen
    0.12
    Act Density 0.026%

    No Known Activations