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

    Neuronpedia

    INDEX
    Explanations

    names, locations, and references to specific individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Gaga" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ership
    -0.76
     AAP
    -0.66
    most
    -0.65
    enegger
    -0.62
     pse
    -0.61
    points
    -0.61
     ubiqu
    -0.60
    ensible
    -0.58
     honesty
    -0.58
     integers
    -0.58
    POSITIVE LOGITS
    aga
    1.10
    ption
    1.02
    vernment
    1.00
    ña
    0.94
    oka
    0.91
    veyard
    0.89
     Siren
    0.88
    iba
    0.87
    BILITY
    0.85
    amaz
    0.82
    Act Density 0.007%

    No Known Activations