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

    Neuronpedia

    INDEX
    Explanations

    citations and author names in academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enas
    -0.16
    oba
    -0.15
    iaux
    -0.15
    ourd
    -0.15
    sdale
    -0.14
    adh
    -0.14
    ursal
    -0.14
    anos
    -0.14
    093
    -0.14
    è¨Ģãģ£ãģŁ
    -0.14
    POSITIVE LOGITS
     di
    0.23
     Vital
    0.20
     Grass
    0.20
     Rossi
    0.19
     Amend
    0.19
     Guerr
    0.18
     Ted
    0.18
     Batt
    0.18
     Pacific
    0.18
     Ming
    0.18
    Act Density 0.093%

    No Known Activations