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

    Neuronpedia

    INDEX
    Explanations

    instances of direct speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    they
    -0.13
    .onNext
    -0.13
    azard
    -0.13
    ãģķãģĽ
    -0.13
    then
    -0.13
    ãģŁãĤģãģ®
    -0.12
    ison
    -0.12
    Ãį
    -0.12
     Airways
    -0.12
    é
    -0.12
    POSITIVE LOGITS
     said
    0.19
     spokesman
    0.18
    aukee
    0.15
    said
    0.15
     spokesperson
    0.14
     added
    0.14
     spokeswoman
    0.14
     оÑĩевид
    0.13
    incerely
    0.13
    ãĤ´ãĥª
    0.13
    Act Density 0.087%

    No Known Activations