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

    Neuronpedia

    INDEX
    Explanations

    patterns related to programming syntax and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    êcher
    -0.72
     esfuer
    -0.58
     chaude
    -0.57
    bersicht
    -0.54
    ategorised
    -0.51
    énération
    -0.51
    gnings
    -0.50
     delgada
    -0.50
    gyű
    -0.49
    rateur
    -0.49
    POSITIVE LOGITS
     Efq
    0.68
     Houſe
    0.59
     themſelves
    0.51
     Diſ
    0.51
     myſelf
    0.51
     pleaſure
    0.51
     himſelf
    0.50
     Majefty
    0.49
     Jefus
    0.48
     ſeveral
    0.48
    Act Density 0.095%

    No Known Activations