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

    Neuronpedia

    INDEX
    Explanations

    text related to referencing and editing in a document

    oai_token-act-pair · gpt-3.5-turbo

    sections related to references or further reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scrim
    -0.68
     seated
    -0.62
     molded
    -0.61
     mentality
    -0.61
     layoffs
    -0.60
     motto
    -0.60
     rece
    -0.60
    ufact
    -0.59
    etheless
    -0.58
     somet
    -0.58
    POSITIVE LOGITS
    References
    1.39
    âĨij
    1.37
    Further
    1.20
    External
    1.16
    ibliography
    1.12
    Notes
    1.09
    Acknowled
    0.99
     References
    0.95
    Sources
    0.92
    ^
    0.91
    Act Density 0.053%

    No Known Activations