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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote significant dates and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orno
    -0.15
    opak
    -0.14
    ách
    -0.14
     tomorrow
    -0.14
    izon
    -0.14
     Freeze
    -0.13
    Datum
    -0.13
    à¹ĥà¸Ļว
    -0.13
    _draft
    -0.13
    nox
    -0.13
    POSITIVE LOGITS
    199
    0.45
    201
    0.43
    200
    0.42
    198
    0.40
    197
    0.34
     February
    0.34
     January
    0.33
    196
    0.32
     December
    0.32
     June
    0.31
    Act Density 0.327%

    No Known Activations