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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afa
    -0.15
    agner
    -0.14
    atham
    -0.14
     Dare
    -0.14
    765
    -0.14
    EventData
    -0.14
    jsc
    -0.13
     Cousins
    -0.13
    .ul
    -0.13
     Simone
    -0.13
    POSITIVE LOGITS
     em
    0.22
    roid
    0.19
    uel
    0.18
    itters
    0.18
    GENCY
    0.17
    tee
    0.17
    erald
    0.17
    esar
    0.16
    .persist
    0.15
    omain
    0.15
    Act Density 0.028%

    No Known Activations