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

    Neuronpedia

    INDEX
    Explanations

    terms related to analysis and research methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .sap
    -0.18
    iland
    -0.17
    glomer
    -0.16
    enting
    -0.16
    orz
    -0.15
    sut
    -0.15
    lingen
    -0.15
    entar
    -0.15
    obus
    -0.14
    illes
    -0.14
    POSITIVE LOGITS
    sis
    0.36
    osis
    0.32
    isis
    0.30
    esis
    0.28
    asis
    0.25
    tic
    0.23
     sis
    0.21
    otic
    0.21
    xis
    0.21
    zing
    0.20
    Act Density 0.061%

    No Known Activations