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

    Neuronpedia

    INDEX
    Explanations

    phrases related to writing and composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ülük
    -0.16
    ouser
    -0.14
    sonian
    -0.14
     Dat
    -0.14
    ãĥ¼ãĥĭ
    -0.13
    isson
    -0.13
    uli
    -0.13
    è±Ĩ
    -0.13
     æ£
    -0.13
     chod
    -0.13
    POSITIVE LOGITS
    UU
    0.16
    oldur
    0.16
    CRY
    0.15
    ekk
    0.15
     Crus
    0.14
    rant
    0.14
    nelle
    0.14
    ast
    0.14
    tors
    0.14
    ziej
    0.14
    Act Density 0.004%

    No Known Activations