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

    Neuronpedia

    INDEX
    Explanations

    relevant text messages indicating communication

    oai_token-act-pair · gpt-3.5-turbo

    references to communication methods, particularly text messages and emails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iculture
    -0.73
    Apply
    -0.70
    aughs
    -0.69
    Construction
    -0.65
     forestry
    -0.65
    oba
    -0.62
     brakes
    -0.61
    ESCO
    -0.61
    Building
    -0.61
     Flavoring
    -0.60
    POSITIVE LOGITS
     exchanged
    1.31
     intercepted
    1.19
     overheard
    1.11
     between
    1.09
     messages
    1.06
     Emails
    0.96
     transcripts
    0.94
     Messages
    0.93
    between
    0.92
     exchanges
    0.92
    Act Density 0.164%

    No Known Activations