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

    Neuronpedia

    INDEX
    Explanations

    unique identifiers or institutional indicators in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ``
    -0.17
     (
    -0.17
     Newcastle
    -0.15
     CSA
    -0.15
     Cosby
    -0.14
     ([
    -0.14
     Berkshire
    -0.14
     DFA
    -0.14
     “[
    -0.13
     Cambodia
    -0.13
    POSITIVE LOGITS
     Lap
    0.40
     lap
    0.28
     Rab
    0.25
    lap
    0.24
     Rad
    0.24
     Rabbit
    0.23
    rabbit
    0.23
    Rad
    0.22
     LAP
    0.22
     rabbits
    0.21
    Act Density 0.003%

    No Known Activations