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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or named entities related to specific organizations, locations, or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, entities, or official titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ°
    -0.61
    GoldMagikarp
    -0.60
     BALL
    -0.60
     looph
    -0.56
    cyl
    -0.56
    count
    -0.54
    PDATE
    -0.53
    minist
    -0.51
     corrid
    -0.51
     Ern
    -0.51
    POSITIVE LOGITS
     respectively
    1.23
     thereto
    0.97
     thereof
    0.96
     therein
    0.87
     alike
    0.87
     thereafter
    0.83
     etc
    0.82
     versa
    0.78
     likewise
    0.72
     accordingly
    0.72
    Act Density 0.672%

    No Known Activations