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

    Neuronpedia

    INDEX
    Explanations

    words related to data and technology infrastructure

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.91
    lain
    -0.79
     Oath
    -0.75
     Pis
    -0.71
    ovie
    -0.70
    ength
    -0.69
     Palestin
    -0.68
     notor
    -0.66
    aska
    -0.66
    folios
    -0.65
    POSITIVE LOGITS
    flow
    1.06
     analytics
    0.94
    frame
    0.93
    iologist
    0.93
     recorder
    0.87
    Transfer
    0.86
     collection
    0.85
    flows
    0.82
    frames
    0.79
     collected
    0.78
    Act Density 0.029%

    No Known Activations