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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of 'place' and instances of 'fake'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.61
    RefNanny
    -0.59
    makeConstraints
    -0.58
     AspNetCore
    -0.58
     userSchema
    -0.56
    richTextPanel
    -0.53
    AnchorTagHelper
    -0.53
     engraçadas
    -0.53
    rungsseite
    -0.52
    elemField
    -0.52
    POSITIVE LOGITS
     fake
    0.69
    fake
    0.64
     faking
    0.56
     Fake
    0.55
    Fake
    0.51
     fakes
    0.48
     atmosphere
    0.42
     дописавши
    0.42
     faked
    0.41
    sive
    0.40
    Act Density 0.049%

    No Known Activations