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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "prairie"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "praise" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ners
    -0.78
    ania
    -0.77
    uala
    -0.76
    bang
    -0.75
    ded
    -0.71
    ocker
    -0.70
    ding
    -0.69
    abases
    -0.69
    NER
    -0.68
    wise
    -0.68
    POSITIVE LOGITS
    irie
    0.98
    ignty
    0.89
    ĺħ
    0.87
    iries
    0.82
     Trace
    0.70
    ction
    0.69
    kt
    0.68
     assurance
    0.66
    Stars
    0.66
     Prairie
    0.65
    Act Density 0.053%

    No Known Activations