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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gennaio
    -0.91
     sappi
    -0.90
     ideolog
    -0.88
     solidar
    -0.86
     manuten
    -0.84
     inverte
    -0.83
     pól
    -0.81
     apparti
    -0.79
     cresce
    -0.78
     potest
    -0.78
    POSITIVE LOGITS
     so
    0.59
     McInt
    0.58
     McLaugh
    0.58
     therefore
    0.58
     and
    0.57
     Vaugh
    0.56
     ecru
    0.55
     anyway
    0.55
    abestanden
    0.53
     chronologically
    0.53
    Act Density 0.539%

    No Known Activations