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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal or political issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     préc
    -0.76
     renfer
    -0.71
     convenable
    -0.68
    Cześć
    -0.65
     tantôt
    -0.65
     quoique
    -0.65
     élar
    -0.64
    muito
    -0.63
     aussitôt
    -0.62
     nettement
    -0.61
    POSITIVE LOGITS
     idr
    0.62
     estekak
    0.62
    moiselle
    0.61
     durs
    0.61
    embley
    0.56
     lele
    0.56
     optik
    0.55
     alps
    0.55
    rrggbb
    0.54
    ensacola
    0.53
    Act Density 0.173%

    No Known Activations