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

    Neuronpedia

    INDEX
    Explanations

    email alerts related to breaking news

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    fig
    -0.74
    flies
    -0.71
    fulness
    -0.70
    abase
    -0.62
    figured
    -0.62
    ivism
    -0.62
    steen
    -0.62
    pex
    -0.60
    wo
    -0.60
    tein
    -0.60
    POSITIVE LOGITS
     Emails
    0.89
    VERTISEMENT
    0.76
    ļéĨĴ
    0.72
     transcript
    0.70
     Transcript
    0.68
    uters
    0.67
     arming
    0.65
     transcripts
    0.64
     Copy
    0.64
     inbox
    0.64
    Act Density 0.010%

    No Known Activations