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

    Neuronpedia

    INDEX
    Explanations

    references to email-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to emails and related communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iasis
    -0.73
    OV
    -0.71
    stad
    -0.71
     Glasgow
    -0.71
    INAL
    -0.69
    scope
    -0.69
     Edinburgh
    -0.69
    stood
    -0.67
    ded
    -0.66
    axis
    -0.66
    POSITIVE LOGITS
     Emails
    1.03
     emails
    0.97
     newsletters
    0.95
     inbox
    0.94
     messages
    0.90
     correspondence
    0.89
    ileaks
    0.89
     exchanged
    0.89
     notifications
    0.85
     pertaining
    0.83
    Act Density 0.030%

    No Known Activations