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

    Neuronpedia

    INDEX
    Explanations

    proper names or aliases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to names and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -0.82
    opian
    -0.73
     benefit
    -0.73
     jars
    -0.70
     incentives
    -0.70
     incentiv
    -0.68
    orrow
    -0.68
    ockets
    -0.67
    SPONSORED
    -0.66
     satisfy
    -0.65
    POSITIVE LOGITS
     "#
    0.88
     Kw
    0.79
     "-
    0.78
     "_
    0.78
     Dai
    0.78
     Vand
    0.77
     Artemis
    0.77
     ''
    0.75
     '
    0.75
     Abu
    0.75
    Act Density 0.217%

    No Known Activations