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

    Neuronpedia

    INDEX
    Explanations

    quotes or references to other sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to citing sources or references in reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RGB
    -0.83
    quer
    -0.82
    orld
    -0.80
    ould
    -0.78
    visors
    -0.76
    tes
    -0.75
    te
    -0.74
    ire
    -0.74
    carry
    -0.73
    itialized
    -0.72
    POSITIVE LOGITS
     unnamed
    1.00
     sources
    0.93
     unspecified
    0.84
     warnings
    0.83
     factors
    0.83
     examples
    0.81
     motivations
    0.79
     unidentified
    0.78
     motives
    0.77
     inconsistencies
    0.77
    Act Density 0.038%

    No Known Activations