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

    Neuronpedia

    INDEX
    Explanations

    references to specific online platforms or technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to social media and digital communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ategories
    -0.75
    bernatorial
    -0.74
    ONSORED
    -0.74
    ilogy
    -0.71
    ufact
    -0.66
    urd
    -0.66
    emetery
    -0.66
    jriwal
    -0.66
    licts
    -0.65
    rodu
    -0.65
    POSITIVE LOGITS
     sparing
    0.96
     wisely
    0.90
     pseudonym
    0.81
     levers
    0.76
     techniques
    0.76
     tools
    0.75
     analogy
    0.74
     gimm
    0.73
     metaphors
    0.72
     extensively
    0.72
    Act Density 0.612%

    No Known Activations