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

    Neuronpedia

    INDEX
    Explanations

    references to specific scientific publications and their citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    als
    -0.14
    ellas
    -0.14
    ieber
    -0.14
     Ngh
    -0.14
    nar
    -0.14
    rels
    -0.13
    .eth
    -0.13
    kola
    -0.13
     shar
    -0.13
    .StatusCode
    -0.12
    POSITIVE LOGITS
    lint
    0.19
    cke
    0.15
    cg
    0.15
     Dra
    0.14
    ãĥĥãĥģ
    0.14
    ļ
    0.14
     outer
    0.14
    ptune
    0.13
     LW
    0.13
    RID
    0.13
    Act Density 0.081%

    No Known Activations