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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical locations or movements

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns indicating ownership or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Wright
    -0.69
     IEEE
    -0.63
     Izan
    -0.62
     Wong
    -0.62
     NETWORK
    -0.62
     Chrys
    -0.62
     Feder
    -0.62
     Corpus
    -0.60
     USPS
    -0.60
    IVERS
    -0.60
    POSITIVE LOGITS
     own
    1.35
     usual
    0.94
     rightful
    0.89
     customary
    0.87
     respective
    0.83
     heels
    0.83
     knees
    0.80
     duties
    0.78
     haun
    0.77
     millenn
    0.76
    Act Density 0.194%

    No Known Activations