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

    Neuronpedia

    INDEX
    Explanations

    email-related terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to news and email communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    own
    -0.85
    itar
    -0.82
    stood
    -0.77
    leaf
    -0.77
    fig
    -0.76
    lust
    -0.75
    ball
    -0.74
    sen
    -0.73
    jury
    -0.73
    flies
    -0.72
    POSITIVE LOGITS
     Emails
    1.34
     Transcript
    0.86
    ÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤÃĥÃĤ
    0.81
     partName
    0.78
     Loading
    0.77
    webkit
    0.77
    VERTISEMENT
    0.76
    allery
    0.76
    catentry
    0.76
     Container
    0.75
    Act Density 0.017%

    No Known Activations