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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technology features or components being built into products

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with the concept of integration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zai
    -0.78
    uku
    -0.74
    yright
    -0.71
    oxic
    -0.69
    entimes
    -0.65
    dan
    -0.63
    ebted
    -0.62
    thora
    -0.62
    chu
    -0.61
    edo
    -0.61
    POSITIVE LOGITS
     adulthood
    0.87
     Valhalla
    0.65
     existence
    0.64
    play
    0.63
     Vegas
    0.63
     infinity
    0.62
     submission
    0.61
     peoples
    0.60
    wards
    0.60
     ob
    0.60
    Act Density 0.060%

    No Known Activations