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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to predictions or expectations about future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aisal
    -0.16
    iena
    -0.16
     Severity
    -0.15
    roperties
    -0.15
    paged
    -0.15
    atron
    -0.14
    ç¯Ģ
    -0.14
     Hou
    -0.14
    ullo
    -0.14
    actor
    -0.14
    POSITIVE LOGITS
     Witt
    0.16
    yll
    0.14
    Ñĩин
    0.13
    ertest
    0.13
    Îŀ
    0.13
    ites
    0.13
    ãĤ¤ãĥĪ
    0.13
     ÙħÙĪرد
    0.13
    عاÙĦ
    0.13
    itt
    0.13
    Act Density 0.005%

    No Known Activations