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

    Neuronpedia

    INDEX
    Explanations

    terms or phrases related to the concept of correspondence

    oai_token-act-pair · gpt-3.5-turbo

    references to correspondence or relationships between different elements or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fare
    -0.75
    uv
    -0.74
    ilers
    -0.71
     helicop
    -0.69
    zan
    -0.69
    spe
    -0.68
    cloth
    -0.67
    uff
    -0.67
    agin
    -0.66
    brid
    -0.66
    POSITIVE LOGITS
    MpServer
    0.74
     Period
    0.72
     corresponding
    0.70
     Dragonbound
    0.70
    alties
    0.69
    ively
    0.69
    ificantly
    0.69
    ingly
    0.67
     MPG
    0.65
     corresponds
    0.64
    Act Density 0.009%

    No Known Activations