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

    Neuronpedia

    INDEX
    Explanations

    assertions that critique the validity or completeness of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acho
    -0.17
    BITS
    -0.16
    ãĤ¿ãĥ¼
    -0.14
    echn
    -0.14
    norm
    -0.14
    otta
    -0.13
    .obtain
    -0.13
    Ñĥди
    -0.13
    icios
    -0.13
    radient
    -0.13
    POSITIVE LOGITS
    ´Ŀ
    0.16
    ovky
    0.15
    Whitespace
    0.15
    Inspectable
    0.14
    Disallow
    0.14
    /stretch
    0.14
     cav
    0.14
     Mong
    0.14
    etag
    0.14
    vre
    0.13
    Act Density 0.404%

    No Known Activations