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

    Neuronpedia

    INDEX
    Explanations

    code-related terminologies and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thy
    -0.15
    sty
    -0.14
    ritz
    -0.14
     once
    -0.14
    utable
    -0.14
    té
    -0.14
     çī
    -0.14
    illard
    -0.14
    rw
    -0.14
    legg
    -0.14
    POSITIVE LOGITS
    hole
    0.18
    pis
    0.15
    aurant
    0.15
    holes
    0.15
    омина
    0.15
    ë£Į
    0.14
    Ïħν
    0.14
     Basic
    0.14
    basic
    0.14
    542
    0.14
    Act Density 0.003%

    No Known Activations