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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "splitting" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lad
    -0.16
    het
    -0.16
    erm
    -0.15
    顺
    -0.15
    hit
    -0.15
    å¤ĩ
    -0.15
    uest
    -0.14
    ous
    -0.14
    usal
    -0.14
    istics
    -0.14
    POSITIVE LOGITS
     split
    0.26
     Split
    0.24
    -split
    0.24
     splits
    0.23
    (split
    0.23
     splitting
    0.23
    Split
    0.22
    split
    0.22
    deaux
    0.22
    .Split
    0.20
    Act Density 0.038%

    No Known Activations