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

    Neuronpedia

    INDEX
    Explanations

    phrases or questions starting with "how to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InSection
    -0.79
    ImageContext
    -0.67
    Personensuche
    -0.66
    UnsafeEnabled
    -0.63
    BASEPATH
    -0.62
     jir
    -0.61
     ProtoMessage
    -0.61
    SceneManagement
    -0.60
    crollView
    -0.59
    posedge
    -0.59
    POSITIVE LOGITS
    howto
    0.94
     如何
    0.94
     Cómo
    0.88
    如何
    0.84
     how
    0.78
     怎样
    0.78
    如何在
    0.78
     איך
    0.78
    Cómo
    0.77
     hogyan
    0.76
    Act Density 0.108%

    No Known Activations