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

    Neuronpedia

    INDEX
    Explanations

    instances of non-standard text formatting and structure within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ?''
    -0.61
     alene
    -0.57
     arşivlendi
    -0.56
    INTEGR
    -0.53
    hati
    -0.53
     الأصل
    -0.52
     PRINCIPAL
    -0.52
     climber
    -0.51
     pères
    -0.51
     pazi
    -0.51
    POSITIVE LOGITS
     betweenstory
    0.82
     FormsModule
    0.70
     etc
    0.66
     cherchés
    0.66
    页面存档备份
    0.63
    bcryptjs
    0.60
    etc
    0.59
     snippetHide
    0.59
    __((
    0.58
    0.58
    Act Density 0.374%

    No Known Activations