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

    Neuronpedia

    INDEX
    Explanations

    number-letter combinations with a dash in between

    oai_token-act-pair · gpt-3.5-turbo

    references to key individuals or entities, particularly in the context of financial or economic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģ«
    -0.70
    schild
    -0.69
    oola
    -0.67
     pregn
    -0.66
    hani
    -0.64
     appre
    -0.63
    zee
    -0.63
    cules
    -0.59
    cular
    -0.59
    ysis
    -0.56
    POSITIVE LOGITS
    oak
    0.61
    cil
    0.56
    veland
    0.56
     sand
    0.54
     Gaul
    0.52
    sector
    0.51
     Tile
    0.51
    ãĤī
    0.50
     Merc
    0.50
     âĨ
    0.49
    Act Density 0.532%

    No Known Activations