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

    Neuronpedia

    INDEX
    Explanations

    mentions or instances of the word "trigger"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hemat
    -0.86
    ately
    -0.82
    esan
    -0.82
    apolis
    -0.79
    ensable
    -0.77
    iance
    -0.76
    cipled
    -0.75
    cott
    -0.73
    ians
    -0.73
    opathy
    -0.73
    POSITIVE LOGITS
     triggering
    1.18
    trigger
    1.13
     triggers
    1.12
     trigger
    1.10
     Trigger
    0.94
     warnings
    0.93
     triggered
    0.92
    chnology
    0.90
    witz
    0.89
     guiActiveUn
    0.79
    Act Density 10.707%

    No Known Activations