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

    Neuronpedia

    INDEX
    Explanations

    statements that have been signed by or related to a specific number of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "by" in various contexts, particularly in reference to authorship or agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uality
    -0.81
    kaya
    -0.73
     resil
    -0.73
    ãĤ£
    -0.71
     ILCS
    -0.70
    redits
    -0.70
    agram
    -0.67
    zona
    -0.67
    wagon
    -0.66
     âĶľâĶĢâĶĢ
    -0.66
    POSITIVE LOGITS
     Senators
    0.76
     Ellen
    0.76
     Senator
    0.75
     governors
    0.74
     economists
    0.72
     economist
    0.72
     Cyrus
    0.71
     Cardinal
    0.71
     Theodore
    0.70
     former
    0.70
    Act Density 0.119%

    No Known Activations