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

    Neuronpedia

    INDEX
    Explanations

    strings of characters containing frequent instances of the pattern "yr"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "year" or variations of it, often linked with numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ou
    -0.85
     Papua
    -0.77
     Ic
    -0.69
     Fiesta
    -0.66
     Canal
    -0.66
     Paragu
    -0.65
    ELS
    -0.64
     Chao
    -0.64
     Machines
    -0.64
     Sahara
    -0.64
    POSITIVE LOGITS
    rha
    1.26
    andom
    0.89
    rr
    0.88
    rh
    0.86
    umph
    0.83
    terday
    0.82
    mph
    0.80
    anny
    0.79
    abbit
    0.78
    hon
    0.77
    Act Density 0.019%

    No Known Activations