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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to personal preferences and ideal conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pestic
    -0.50
    ADVERTISEMENT
    -0.47
    ":[{"
    -0.46
     compr
    -0.46
     behavi
    -0.45
    resents
    -0.44
    hang
    -0.44
     blight
    -0.44
    ãĢİ
    -0.44
     commod
    -0.43
    POSITIVE LOGITS
    .)
    2.42
    .")
    2.40
    .).
    2.35
     .)
    2.35
    ').
    2.30
    ?).
    2.22
    !).
    2.22
    .),
    2.21
    )."
    2.19
    !)
    2.16
    Act Density 1.151%

    No Known Activations