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

    Neuronpedia

    INDEX
    Explanations

    phrases related to inviting or welcoming someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to invitations and welcoming interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     correlate
    -0.67
    tein
    -0.64
     gears
    -0.62
     transcript
    -0.62
     organs
    -0.61
     indexes
    -0.61
     scales
    -0.60
     elapsed
    -0.58
     cass
    -0.58
     consumed
    -0.57
    POSITIVE LOGITS
    riott
    0.89
    soType
    0.78
     audiences
    0.74
     dign
    0.71
     parties
    0.71
    SpaceEngineers
    0.69
     explorers
    0.68
    ington
    0.68
    prises
    0.68
    izons
    0.68
    Act Density 0.152%

    No Known Activations