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

    Neuronpedia

    INDEX
    Explanations

    phrases related to copying and pasting text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "copy and paste" actions or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.73
    FML
    -0.69
    ufact
    -0.68
    ailability
    -0.68
    baum
    -0.66
     fare
    -0.63
    CW
    -0.62
     exception
    -0.62
    natureconservancy
    -0.62
    ghai
    -0.62
    POSITIVE LOGITS
    auga
    0.83
    adelphia
    0.79
     chloride
    0.71
    antha
    0.71
    otom
    0.71
    opter
    0.68
    Ń·
    0.66
    Quantity
    0.64
    thia
    0.63
    nir
    0.62
    Act Density 0.593%

    No Known Activations