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

    Neuronpedia

    INDEX
    Explanations

    sections with substantial scientific or technical content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /*
    -0.73
     Италијани
    -0.66
     bezeichneter
    -0.61
    UnsafeEnabled
    -0.60
    IVersion
    -0.58
    Personendaten
    -0.56
    Portály
    -0.56
    Ecotoxicity
    -0.56
    coroutines
    -0.55
    posables
    -0.54
    POSITIVE LOGITS
    eqn
    0.87
    IsContent
    0.59
     Diſ
    0.59
     Majefty
    0.58
     fevere
    0.58
     itſelf
    0.57
    ſelves
    0.57
    Revenir
    0.56
    发表于
    0.56
    Tikang
    0.55
    Act Density 0.016%

    No Known Activations