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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific names or subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, organizations, and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    laus
    -1.04
    MENT
    -0.85
    Magazine
    -0.82
    MENTS
    -0.80
    strate
    -0.79
    OUND
    -0.78
    ãģĨ
    -0.78
    bite
    -0.76
    Scale
    -0.74
    ORED
    -0.74
    POSITIVE LOGITS
     swe
    0.75
     lyn
    0.74
     earners
    0.72
    ribune
    0.71
    izens
    0.70
    iners
    0.69
     Tribune
    0.69
    liner
    0.68
     ministry
    0.68
     hubs
    0.67
    Act Density 0.023%

    No Known Activations