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

    Neuronpedia

    INDEX
    Explanations

    snippets of code or programming elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erb
    -0.15
     wh
    -0.15
    aste
    -0.15
    ãģıãĤĮ
    -0.14
    arrant
    -0.14
    izen
    -0.14
     stm
    -0.14
     hakk
    -0.13
     cast
    -0.13
    wen
    -0.13
    POSITIVE LOGITS
    eryl
    0.15
    undle
    0.15
    -UA
    0.14
     Ziel
    0.14
    ortal
    0.14
    559
    0.14
    åĽŀ
    0.13
     Unblock
    0.13
    deaux
    0.13
    _CAPACITY
    0.13
    Act Density 0.017%

    No Known Activations