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

    Neuronpedia

    INDEX
    Explanations

    words indicating interaction or action involving other entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olith
    -0.17
    ird
    -0.15
    OCI
    -0.15
    ţi
    -0.14
    990
    -0.14
    roe
    -0.14
    RTOS
    -0.14
    phant
    -0.14
    @d
    -0.14
    arf
    -0.13
    POSITIVE LOGITS
    scoped
    0.14
    YTE
    0.14
    ŃIJï¸ı
    0.14
    ÏĦÎŃ
    0.14
    pedia
    0.13
    _IGNORE
    0.13
    clerosis
    0.13
    onda
    0.13
     bo
    0.13
     Reed
    0.13
    Act Density 0.002%

    No Known Activations