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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases related to relevance or importance

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases that indicate relevance or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hesda
    -0.74
    owered
    -0.72
    cker
    -0.72
    jah
    -0.71
    rette
    -0.71
    riage
    -0.70
    boats
    -0.69
    rie
    -0.67
    pload
    -0.67
    boat
    -0.67
    POSITIVE LOGITS
     footnote
    0.78
     material
    0.77
     thereto
    0.76
     information
    0.71
     considerations
    0.71
    ioned
    0.69
    ively
    0.68
     contextual
    0.68
     context
    0.68
     Material
    0.66
    Act Density 0.036%

    No Known Activations