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

    Neuronpedia

    INDEX
    Explanations

    hashtags and symbols often used in technical or specialized contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nelly
    -0.17
    ullo
    -0.16
    .TabStop
    -0.16
    arias
    -0.15
     yours
    -0.15
    ecko
    -0.15
    kening
    -0.14
    аÑĢод
    -0.14
     Fare
    -0.14
    áng
    -0.13
    POSITIVE LOGITS
    els
    0.16
    ertz
    0.15
    aec
    0.15
    ãģıãĤī
    0.14
     Lump
    0.14
    .sax
    0.14
    γγ
    0.14
    Alg
    0.14
     Learned
    0.14
    cmd
    0.14
    Act Density 0.005%

    No Known Activations