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

    Neuronpedia

    INDEX
    Explanations

    phrases related to numerical values and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loven
    -0.16
    olum
    -0.15
    áz
    -0.14
     miá»ĩng
    -0.14
     Nam
    -0.14
    abi
    -0.14
    ãĥĸãĥ«
    -0.14
     Priv
    -0.14
     fmt
    -0.14
     designer
    -0.13
    POSITIVE LOGITS
    ÏĢε
    0.18
    iese
    0.17
     Anc
    0.15
    Ñģп
    0.14
    atcher
    0.14
    igrations
    0.14
    aye
    0.14
     Cly
    0.14
     Gors
    0.14
    åħ¥ãĤĬ
    0.14
    Act Density 0.030%

    No Known Activations