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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting elements commonly used in programming and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    änner
    -0.15
    ÙģØ´
    -0.15
    enou
    -0.14
     Late
    -0.14
     late
    -0.14
    anax
    -0.14
    APPER
    -0.14
     Mus
    -0.14
    ourse
    -0.13
     pl
    -0.13
    POSITIVE LOGITS
    Y
    0.22
    FT
    0.20
    ordinal
    0.18
     Shorts
    0.16
    j
    0.16
    Ord
    0.15
    POS
    0.15
    m
    0.15
    U
    0.15
    H
    0.15
    Act Density 0.001%

    No Known Activations