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

    Neuronpedia

    INDEX
    Explanations

    textual patterns or formatting elements in the input

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelBuilder
    -0.93
     يتيمه
    -0.88
    rungsseite
    -0.86
     calendriers
    -0.83
     Cohn
    -0.83
    AddressBook
    -0.82
     Nye
    -0.81
     propOrder
    -0.80
     Englewood
    -0.80
    Moll
    -0.79
    POSITIVE LOGITS
    ><
    1.74
    "><
    1.33
    ;"><
    1.07
    ="#"><
    1.06
    =""><
    1.00
    '><
    0.95
     <
    0.86
     /><
    0.83
    <
    0.83
    ///<
    0.82
    Act Density 0.031%

    No Known Activations