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

    Neuronpedia

    INDEX
    Explanations

    pairs of words related to communication or interaction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "interact" and its related usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    price
    -0.76
     teasp
    -0.75
    corn
    -0.73
     quart
    -0.69
    quad
    -0.67
    moon
    -0.67
    orah
    -0.65
     weighed
    -0.64
     priced
    -0.62
    hower
    -0.62
    POSITIVE LOGITS
     passers
    0.72
     peers
    0.72
     clients
    0.72
     strangers
    0.70
     constituents
    0.69
    =-=-=-=-
    0.68
     networks
    0.67
     stakeholders
    0.66
     coworkers
    0.64
    aline
    0.64
    Act Density 0.166%

    No Known Activations