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

    Neuronpedia

    INDEX
    Explanations

    proper names and titles

    oai_token-act-pair · gpt-3.5-turbo

    prominent names or titles related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.66
     hindsight
    -0.62
     clubhouse
    -0.61
    LEASE
    -0.57
    ãĤ¨ãĥ«
    -0.52
     symbolism
    -0.52
     interchangeable
    -0.51
     Wolves
    -0.51
     equivalents
    -0.51
     undecided
    -0.51
    POSITIVE LOGITS
    inski
    0.87
    ovich
    0.83
    mann
    0.82
    enberg
    0.78
    stad
    0.78
    auer
    0.77
    ich
    0.76
    ensen
    0.76
    endor
    0.75
     (@
    0.73
    Act Density 0.765%

    No Known Activations