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

    Neuronpedia

    INDEX
    Explanations

    references to programming or technical specifications, particularly within a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emony
    -0.15
    adr
    -0.14
    onda
    -0.14
    /we
    -0.14
    yan
    -0.14
    uje
    -0.14
    vim
    -0.13
     ola
    -0.13
    ynos
    -0.13
     Guidance
    -0.13
    POSITIVE LOGITS
    atform
    0.17
    иÑĤив
    0.16
    SSF
    0.15
    _TERMIN
    0.15
    TRS
    0.15
    angl
    0.14
    ฬ
    0.14
     lump
    0.14
    iese
    0.14
     Raum
    0.14
    Act Density 0.211%

    No Known Activations