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

    Neuronpedia

    INDEX
    Explanations

    usage of quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.19
     “[
    -0.16
     “âĢ¦
    -0.15
    zahl
    -0.15
    StateManager
    -0.15
    /documentation
    -0.14
    ¬ģ
    -0.14
    ...',↵
    -0.13
    669
    -0.13
    urst
    -0.13
    POSITIVE LOGITS
    ibi
    0.16
    aci
    0.14
    {'
    0.14
    Ìĥ
    0.14
    Ë
    0.14
    -"
    0.13
    pch
    0.13
    lite
    0.13
    AGMA
    0.13
    umb
    0.13
    Act Density 0.220%

    No Known Activations