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

    Neuronpedia

    INDEX
    Explanations

    introductory phrases that indicate the start of a list or sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÅĻel
    -0.18
    vid
    -0.15
    ampler
    -0.14
     topLeft
    -0.14
    oft
    -0.14
    ATABASE
    -0.13
     syn
    -0.13
    има
    -0.13
    kö
    -0.13
    Japanese
    -0.13
    POSITIVE LOGITS
    idan
    0.17
    entine
    0.15
    tol
    0.14
    ãĥ³ãĥĨ
    0.14
     ddl
    0.14
     Ø®ÙĪب
    0.14
    erset
    0.14
    IDA
    0.14
    utom
    0.14
    STREAM
    0.13
    Act Density 0.055%

    No Known Activations