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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and relationships involving conditions, distributions, and parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     society
    -0.15
    abbo
    -0.14
    ritable
    -0.14
    legg
    -0.14
    edi
    -0.14
    ÑĩеÑģ
    -0.14
    aggi
    -0.14
    etch
    -0.14
    Edition
    -0.14
     Buffered
    -0.13
    POSITIVE LOGITS
    anja
    0.20
    oud
    0.17
    enga
    0.17
    ophe
    0.16
    izabeth
    0.15
    aksi
    0.14
    å£
    0.14
    resh
    0.14
    ITHER
    0.14
    ou
    0.13
    Act Density 0.094%

    No Known Activations