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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and proper nouns, particularly related to personal and product names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éo
    -0.18
    ARGIN
    -0.16
    erval
    -0.16
    .gz
    -0.15
    eon
    -0.15
    ussen
    -0.15
    readcr
    -0.15
    iš
    -0.14
     ofs
    -0.14
    obby
    -0.14
    POSITIVE LOGITS
    -vous
    0.28
    r
    0.23
    vous
    0.22
    ipped
    0.19
    ึà¹Ī
    0.19
    ircon
    0.18
    s
    0.18
    OOM
    0.18
    ephir
    0.18
    ebra
    0.17
    Act Density 0.320%

    No Known Activations