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

    Neuronpedia

    INDEX
    Explanations

    references to various societal eras and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    untime
    -0.14
    atsby
    -0.14
     wherever
    -0.14
    onda
    -0.14
    ilar
    -0.14
     upon
    -0.14
    ooter
    -0.13
    ortho
    -0.13
    ookies
    -0.13
    à¥ĩस
    -0.13
    POSITIVE LOGITS
     marked
    0.34
     characterized
    0.31
     character
    0.31
     Character
    0.29
    marked
    0.29
    character
    0.28
     caracter
    0.28
     defined
    0.27
    -character
    0.26
    Character
    0.26
    Act Density 0.102%

    No Known Activations