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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social interaction or communication

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to connecting or interacting with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    price
    -0.82
     teasp
    -0.74
    corn
    -0.70
    done
    -0.66
    quad
    -0.66
    fighter
    -0.66
     weighed
    -0.63
    moon
    -0.62
    meal
    -0.60
    vu
    -0.59
    POSITIVE LOGITS
     peers
    0.81
     strangers
    0.79
    inge
    0.73
     fellow
    0.71
     passers
    0.70
     Heavenly
    0.70
    inges
    0.69
     coworkers
    0.67
     clients
    0.65
     Osc
    0.65
    Act Density 0.118%

    No Known Activations