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

    Neuronpedia

    INDEX
    Explanations

    phrases related to possession or involvement in specific events or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to possession and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ochond
    -0.84
    athy
    -0.83
    trak
    -0.79
    imet
    -0.78
    Ö¼
    -0.77
    ichita
    -0.76
    nery
    -0.74
    wic
    -0.73
    iva
    -0.71
    omet
    -0.70
    POSITIVE LOGITS
     capacities
    0.66
     Humanity
    0.62
     Friendship
    0.62
     foreigners
    0.61
     RTX
    0.60
     Content
    0.60
     MF
    0.58
     both
    0.57
     specialization
    0.57
     Curious
    0.56
    Act Density 0.112%

    No Known Activations