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

    Neuronpedia

    INDEX
    Explanations

    messages or communication-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to messages being sent or received

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    culus
    -0.74
    riages
    -0.74
     Simulator
    -0.64
     stagn
    -0.62
     stagnant
    -0.61
     Brune
    -0.61
     peas
    -0.60
     liberties
    -0.58
    ackets
    -0.58
     Railway
    -0.58
    POSITIVE LOGITS
    mails
    0.76
     WhatsApp
    0.72
     greets
    0.72
     greeted
    0.71
     voic
    0.70
     greeting
    0.69
     memos
    0.69
    plain
    0.69
    mail
    0.67
     messages
    0.67
    Act Density 0.501%

    No Known Activations