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

    Neuronpedia

    INDEX
    Explanations

    references to rats

    oai_token-act-pair · gpt-3.5-turbo

    references to rats and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ½
    -0.77
    alach
    -0.69
    qua
    -0.69
    »Ĵ
    -0.68
    ¬¼
    -0.68
     unlaw
    -0.68
    rity
    -0.62
    indal
    -0.62
     Sikh
    -0.60
    irit
    -0.60
    POSITIVE LOGITS
    chet
    1.19
    holes
    0.97
    che
    0.89
    dog
    0.87
    fish
    0.83
    ented
    0.83
    lings
    0.81
    atos
    0.80
    dies
    0.79
    cat
    0.79
    Act Density 0.015%

    No Known Activations