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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of rats

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rats and rat-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.71
    Ļ½
    -0.70
    irit
    -0.68
     Cyprus
    -0.67
     unlaw
    -0.64
    PLIED
    -0.64
    uries
    -0.63
    «ĺ
    -0.63
    conservancy
    -0.62
    rity
    -0.62
    POSITIVE LOGITS
    chet
    1.31
    che
    0.95
    atos
    0.90
    holes
    0.87
    ting
    0.85
    rice
    0.82
    kin
    0.81
    mone
    0.79
    ty
    0.78
    ifiers
    0.78
    Act Density 0.022%

    No Known Activations