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

    Neuronpedia

    INDEX
    Explanations

    words that indicate involvement or responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isc
    -0.16
    obra
    -0.15
    undry
    -0.14
    _override
    -0.14
    reen
    -0.14
    ãĥ¼ãĤ¹
    -0.14
    ø
    -0.13
    _MIX
    -0.13
    .mx
    -0.13
     omin
    -0.13
    POSITIVE LOGITS
    ekk
    0.17
    petto
    0.16
    ÑĢаÑĩ
    0.15
    aç
    0.15
    _IOC
    0.15
    éf
    0.15
    622
    0.14
    acerb
    0.14
    sk
    0.14
    atile
    0.14
    Act Density 0.007%

    No Known Activations