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

    Neuronpedia

    INDEX
    Explanations

    sentences that summarize overall assessments or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uels
    -0.15
    arat
    -0.15
    /../
    -0.14
    iterals
    -0.14
    iffs
    -0.14
    ç³
    -0.14
    obili
    -0.14
    -NLS
    -0.13
    wy
    -0.13
    opsis
    -0.13
    POSITIVE LOGITS
    zip
    0.15
    rellas
    0.14
    ativity
    0.14
    /legal
    0.14
    ption
    0.14
    udden
    0.13
    ETS
    0.13
    Crud
    0.13
    odian
    0.13
    éĹ
    0.13
    Act Density 0.038%

    No Known Activations