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

    Neuronpedia

    INDEX
    Explanations

    references to media, especially titles of books or songs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModelAndView
    -0.51
    Hentet
    -0.44
     bevis
    -0.43
    ЗУ
    -0.42
     
    -0.42
     maybe
    -0.41
     fokus
    -0.41
    수
    -0.41
     echa
    -0.41
     hozz
    -0.41
    POSITIVE LOGITS
     myſelf
    0.84
    ſelf
    0.80
    ſelves
    0.79
     Majefty
    0.73
    aratus
    0.72
     мәкалә
    0.71
    TagMode
    0.71
     Италијани
    0.70
     Мексичка
    0.69
     Efq
    0.67
    Act Density 0.479%

    No Known Activations