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

    Neuronpedia

    INDEX
    Explanations

    names and terms related to specific individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     musíte
    -0.53
    dicionado
    -0.52
    XtraEditors
    -0.48
    няют
    -0.47
    าหลี
    -0.47
    Diweddarwch
    -0.46
    lüğ
    -0.45
     udaler
    -0.44
    GINIA
    -0.43
    ridged
    -0.42
    POSITIVE LOGITS
     indestru
    0.98
     nephe
    0.98
     Ne
    0.97
     philanth
    0.97
     compréhen
    0.96
     Neop
    0.95
     accla
    0.95
     encomp
    0.94
     shenan
    0.93
     inev
    0.92
    Act Density 0.125%

    No Known Activations