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

    Neuronpedia

    INDEX
    Explanations

    the beginning or structural elements of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drey
    -0.58
     por
    -0.54
     cà
    -0.54
    leria
    -0.53
     bezeichneter
    -0.52
     mano
    -0.52
     main
    -0.52
    WindowConstants
    -0.51
     Fle
    -0.50
    s
    -0.49
    POSITIVE LOGITS
     BoxFit
    0.95
    ftagPool
    0.90
     Shakspeare
    0.85
     auffi
    0.84
     Efq
    0.83
     dieß
    0.76
    CloseOperation
    0.75
    istoitu
    0.74
     houſe
    0.73
    MockBean
    0.73
    Act Density 0.098%

    No Known Activations