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

    Neuronpedia

    INDEX
    Explanations

    phrases related to adages and slogans

    oai_token-act-pair · gpt-3.5-turbo

    references to common sayings or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     appointments
    -0.76
    endars
    -0.75
    NetMessage
    -0.72
     contrace
    -0.70
    ockets
    -0.68
    aples
    -0.66
     contracting
    -0.66
    gur
    -0.63
    fman
    -0.62
     Instit
    -0.61
    POSITIVE LOGITS
     uttered
    1.26
    phrase
    1.05
     sung
    1.00
     coined
    0.96
    ology
    0.93
     echoing
    0.90
     phrase
    0.88
     ãĢĮ
    0.86
     implying
    0.84
    iom
    0.84
    Act Density 0.097%

    No Known Activations