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

    Neuronpedia

    INDEX
    Explanations

    specific references to people, places, and their relationships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wegen
    -0.46
     severally
    -0.43
    gmt
    -0.40
    amsmath
    -0.40
    ferd
    -0.38
     because
    -0.37
    рг
    -0.37
     numer
    -0.37
    alised
    -0.36
     flag
    -0.35
    POSITIVE LOGITS
     betweenstory
    0.58
    EndContext
    0.57
    #
    0.53
    dafx
    0.52
     للمعارف
    0.51
     Chwiliwch
    0.49
    farwydd
    0.48
    ViewImports
    0.48
    ⓧ
    0.47
    AISSEE
    0.46
    Act Density 0.836%

    No Known Activations