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

    Neuronpedia

    INDEX
    Explanations

    phrases related to compliance and documentation requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    as
    -0.15
    ca
    -0.15
     Gong
    -0.15
     serv
    -0.15
     modern
    -0.14
     fre
    -0.14
    preh
    -0.14
    om
    -0.14
     Ba
    -0.14
    -br
    -0.14
    POSITIVE LOGITS
    uce
    0.16
    ÑĶв
    0.16
    aja
    0.15
    ÑĪин
    0.14
    UCE
    0.14
    oze
    0.14
    harma
    0.14
    á»Ńa
    0.14
    incer
    0.14
    &P
    0.14
    Act Density 0.066%

    No Known Activations