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

    Neuronpedia

    INDEX
    Explanations

    personal names or terms related to a person

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "udd," likely referring to a specific subject or term that dominates the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lapse
    -0.74
    pora
    -0.65
    GW
    -0.64
     vengeance
    -0.62
     flare
    -0.62
     fabrication
    -0.62
     Freedom
    -0.61
    FE
    -0.60
    Frag
    -0.58
     lobe
    -0.58
    POSITIVE LOGITS
    ying
    1.00
    udd
    0.96
    ington
    0.95
    ernaut
    0.94
    issance
    0.88
    emouth
    0.85
    hari
    0.84
    odge
    0.83
    itions
    0.83
    ski
    0.82
    Act Density 0.007%

    No Known Activations