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

    Neuronpedia

    INDEX
    Explanations

    representatives from various organizations or institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of representatives within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.78
    spir
    -0.77
    osure
    -0.72
    fall
    -0.72
    \\\\\\\\\\\\\\\\
    -0.71
     Pound
    -0.71
    seed
    -0.69
     [|
    -0.67
    aughs
    -0.67
    forth
    -0.66
    POSITIVE LOGITS
    hips
    1.31
    hip
    0.88
    ratulations
    0.82
    rors
    0.81
     representatives
    0.76
     warr
    0.75
    ervatives
    0.75
    maid
    0.74
    chool
    0.74
    pring
    0.74
    Act Density 0.019%

    No Known Activations