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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply comparison or categorization of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olo
    -0.17
    ittel
    -0.16
    anken
    -0.16
    orz
    -0.15
    reon
    -0.14
    edu
    -0.14
     org
    -0.14
    ongs
    -0.14
    ntag
    -0.14
     Sloan
    -0.14
    POSITIVE LOGITS
    aggio
    0.16
    æ¸Ī
    0.15
    LEV
    0.15
     Satoshi
    0.15
    cant
    0.15
     Cant
    0.14
    chwitz
    0.14
    å¶
    0.14
    ckill
    0.14
    stery
    0.14
    Act Density 0.280%

    No Known Activations