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

    Neuronpedia

    INDEX
    Explanations

    words that convey degrees of certainty or specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ø°
    -0.18
    183
    -0.17
    827
    -0.16
    atz
    -0.16
    alias
    -0.16
    duit
    -0.15
    302
    -0.15
    iais
    -0.14
    ocked
    -0.14
    058
    -0.14
    POSITIVE LOGITS
    ighton
    0.15
    ãĤ«ãĥ¼
    0.15
     Ler
    0.15
    à¸ĵà¸ij
    0.15
     Barton
    0.14
     autoc
    0.14
    ackson
    0.14
    ãĥ¼ãĤ¹
    0.13
     Solomon
    0.13
    .amazonaws
    0.13
    Act Density 0.002%

    No Known Activations