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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to friendships and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ourcing
    -0.75
    outheast
    -0.71
    etting
    -0.69
    ettings
    -0.66
    ettlement
    -0.61
    ittered
    -0.61
    earchers
    -0.61
    ense
    -0.60
    lash
    -0.60
     clustered
    -0.59
    POSITIVE LOGITS
    hood
    0.87
    's
    0.87
    mates
    0.85
    mate
    0.83
     Theo
    0.80
     Jacques
    0.79
     Philip
    0.79
     Jaime
    0.78
     Freddie
    0.78
     Joseph
    0.77
    Act Density 0.189%

    No Known Activations