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

    Neuronpedia

    INDEX
    Explanations

    references to digital messages or communication methods

    oai_token-act-pair · gpt-3.5-turbo

    references to text messages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.84
    aughs
    -0.78
    engeance
    -0.76
    arte
    -0.73
    PDATE
    -0.67
    rowd
    -0.67
    undai
    -0.66
    iery
    -0.66
    rowing
    -0.66
    emale
    -0.65
    POSITIVE LOGITS
     messages
    1.02
     Messages
    0.91
    mith
    0.86
     goodbye
    0.84
    Message
    0.84
    message
    0.81
    ipop
    0.81
     inbox
    0.80
     message
    0.80
    boxes
    0.79
    Act Density 0.030%

    No Known Activations