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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic citations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maneu
    -1.98
     shenan
    -1.96
     unspeak
    -1.96
     hairc
    -1.95
     impra
    -1.93
     disagre
    -1.92
     increa
    -1.89
     apprehen
    -1.89
     depic
    -1.88
     indestru
    -1.87
    POSITIVE LOGITS
     kosme
    0.86
     silikon
    0.81
     alkoh
    0.79
     pól
    0.76
     konserv
    0.74
     radikal
    0.72
     solidar
    0.72
     kabel
    0.72
     kontrak
    0.70
     minimalis
    0.69
    Act Density 0.144%

    No Known Activations