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

    Neuronpedia

    INDEX
    Explanations

    words related to connecting with people

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to connection and interaction with others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    price
    -0.90
    corn
    -0.74
     followed
    -0.63
    lette
    -0.63
    atel
    -0.62
    BALL
    -0.62
    Attempt
    -0.61
    done
    -0.61
    trump
    -0.59
    +=
    -0.59
    POSITIVE LOGITS
     stakeholders
    0.96
     peers
    0.96
     strangers
    0.96
     constituents
    0.93
     audiences
    0.93
     fellow
    0.89
     passers
    0.89
     locals
    0.88
     surroundings
    0.87
     listeners
    0.87
    Act Density 0.316%

    No Known Activations