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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "By" indicating authorship or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .Registry
    -0.15
    à¤Ī
    -0.15
    aye
    -0.14
    solete
    -0.14
    åł¡
    -0.14
    ами
    -0.14
    ãģı
    -0.14
     Cove
    -0.13
    ands
    -0.13
    stm
    -0.13
    POSITIVE LOGITS
     contrast
    0.21
     admin
    0.19
    contrast
    0.17
     virtue
    0.17
     definition
    0.16
     chance
    0.16
    rd
    0.16
    (By
    0.16
    -election
    0.15
     Staff
    0.15
    Act Density 0.018%

    No Known Activations