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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of people, places, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various subjects or individuals within a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ples
    -0.74
    rang
    -0.73
    Reviewer
    -0.73
     teasp
    -0.72
    oided
    -0.68
    pmwiki
    -0.68
    SourceFile
    -0.67
    quartered
    -0.66
    urden
    -0.65
    IAL
    -0.65
    POSITIVE LOGITS
     ours
    0.81
     Julius
    0.75
    yip
    0.73
     Ceres
    0.70
     Crist
    0.70
     Philip
    0.70
     Fritz
    0.69
     Jeremiah
    0.69
     Rodriguez
    0.68
     Machina
    0.68
    Act Density 0.035%

    No Known Activations