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

    Neuronpedia

    INDEX
    Explanations

    references to nerdy culture or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    (%)
    -0.59
     strategia
    -0.57
     résult
    -0.53
     valutazione
    -0.53
     kef
    -0.53
     Bx
    -0.52
     Atm
    -0.52
     umo
    -0.52
     arxiv
    -0.51
     Adj
    -0.51
    POSITIVE LOGITS
    <bos>
    0.73
     Bárbara
    0.61
     getAge
    0.61
     childhood
    0.58
     poulet
    0.58
     curé
    0.57
     damals
    0.57
     capitaine
    0.56
     Mère
    0.53
     getVersion
    0.53
    Act Density 0.609%

    No Known Activations