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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discreet communication or secrets being shared

    oai_token-act-pair · gpt-3.5-turbo

    terms related to whispering and subtle communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arcity
    -0.80
    ouf
    -0.78
    onut
    -0.76
    aredevil
    -0.72
    aples
    -0.72
    ordan
    -0.69
    unes
    -0.69
    nea
    -0.69
    ĻĤ
    -0.67
    bard
    -0.67
    POSITIVE LOGITS
     whisper
    1.30
     whispering
    1.17
     whispers
    1.09
     aloud
    1.00
     whispered
    0.87
     omin
    0.86
     louder
    0.85
     softly
    0.83
    ingly
    0.76
     murm
    0.75
    Act Density 0.016%

    No Known Activations