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

    Neuronpedia

    INDEX
    Explanations

    phrases related to policy making and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to discussions about industry transformation and regulatory measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Born
    -0.70
     famously
    -0.66
     adorable
    -0.65
     fame
    -0.64
     Glow
    -0.61
     Sheen
    -0.60
     Famous
    -0.60
     Cells
    -0.59
     Originally
    -0.58
    Born
    -0.58
    POSITIVE LOGITS
    )."
    0.99
    ."[
    0.97
    .""
    0.95
    '."
    0.90
    ."
    0.89
    .'"
    0.88
    ]."
    0.88
    ".[
    0.84
     ourselves
    0.84
    .''
    0.83
    Act Density 1.189%

    No Known Activations