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

    Neuronpedia

    INDEX
    Explanations

    words related to different types of resources and their uses

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social media and entertainment platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minist
    -0.67
    ukong
    -0.59
     EAR
    -0.54
    Reviewer
    -0.54
    JM
    -0.52
    ensional
    -0.51
     Conj
    -0.51
    cture
    -0.50
     tremend
    -0.50
     Kathryn
    -0.49
    POSITIVE LOGITS
     etc
    1.02
    âĢ¦)
    0.79
    )."
    0.73
    ).[
    0.72
     alike
    0.67
    ).
    0.62
    )'
    0.62
    );
    0.62
    )/
    0.62
    )—
    0.61
    Act Density 0.959%

    No Known Activations