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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making connections or building relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate connection or interaction between people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    price
    -0.82
    atel
    -0.73
    fighter
    -0.73
     teasp
    -0.69
    corn
    -0.67
    quad
    -0.66
    done
    -0.66
    vu
    -0.64
    hower
    -0.63
    meal
    -0.61
    POSITIVE LOGITS
     strangers
    0.95
     coworkers
    0.90
     regards
    0.89
     peers
    0.88
     fellow
    0.87
     stakeholders
    0.82
     constituents
    0.81
    stood
    0.80
     passers
    0.80
     regard
    0.80
    Act Density 0.170%

    No Known Activations