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

    Neuronpedia

    INDEX
    Explanations

    phrases related to statistical or numerical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     restera
    -0.74
     prendra
    -0.73
     viciss
    -0.71
     Souha
    -0.67
     Czechos
    -0.66
     compréhen
    -0.66
     philanth
    -0.66
     devint
    -0.63
     encomp
    -0.63
    Vaata
    -0.62
    POSITIVE LOGITS
     estekak
    0.65
     препратки
    0.64
    ,
    0.56
    /**
    0.54
    Havolalar
    0.54
    tanleria
    0.53
    <bos>
    0.51
    luia
    0.51
     lèvres
    0.51
     tetrachloride
    0.50
    Act Density 0.209%

    No Known Activations