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

    Neuronpedia

    INDEX
    Explanations

    sentiments about personal preferences and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.19
    oot
    -0.17
    nam
    -0.16
    263
    -0.15
     larg
    -0.15
    ile
    -0.15
    305
    -0.15
    ewire
    -0.14
    ardo
    -0.14
    辺
    -0.14
    POSITIVE LOGITS
     anale
    0.15
    bcd
    0.15
    ãĥ«ãĥĪ
    0.15
     DISCLAIM
    0.15
    оÑģÑĮ
    0.14
    bestos
    0.14
     OTHERWISE
    0.14
    icha
    0.14
    haus
    0.14
    лÑĮÑĤ
    0.14
    Act Density 0.122%

    No Known Activations