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

    Neuronpedia

    INDEX
    Explanations

    boolean values and expressions indicating truth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lor
    -0.17
    ÏĢÏīÏĤ
    -0.15
    etag
    -0.15
    ocks
    -0.15
    .resume
    -0.15
    rei
    -0.15
    ettes
    -0.14
    reas
    -0.14
    lore
    -0.14
    OPER
    -0.14
    POSITIVE LOGITS
    /false
    0.26
    hetic
    0.17
    ushima
    0.16
    ilden
    0.16
    ongs
    0.16
    oplast
    0.15
    izoph
    0.14
    arem
    0.14
     Ging
    0.14
    compression
    0.14
    Act Density 0.041%

    No Known Activations