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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical properties and measurements

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and concepts related to laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    estern
    -0.68
    GW
    -0.61
    umbai
    -0.59
    espie
    -0.53
    ULAR
    -0.52
    atform
    -0.51
    phabet
    -0.51
     millenn
    -0.51
     theoret
    -0.51
    ipeg
    -0.51
    POSITIVE LOGITS
    *.
    1.04
    .?
    0.99
     lest
    0.92
    .*
    0.92
    .
    0.89
    ãĢĤ
    0.87
    .</
    0.85
    .''.
    0.85
    .'
    0.85
    ."
    0.83
    Act Density 0.781%

    No Known Activations