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

    Neuronpedia

    INDEX
    Explanations

    instances of official communication like letters, statements, and memos

    oai_token-act-pair · gpt-3.5-turbo

    documents or communications such as letters and statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sake
    -0.59
    putable
    -0.57
    ayed
    -0.57
     Thieves
    -0.56
     distant
    -0.56
    rising
    -0.56
     newcomers
    -0.56
     lanes
    -0.55
    pires
    -0.55
    cakes
    -0.54
    POSITIVE LOGITS
     outlining
    0.87
     thanking
    0.86
     titled
    0.81
     apologizing
    0.77
     stating
    0.76
     denouncing
    0.74
     recommending
    0.73
     saying
    0.73
     alleging
    0.73
     condem
    0.73
    Act Density 0.254%

    No Known Activations