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

    Neuronpedia

    INDEX
    Explanations

    references to special events or occasions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PerformLayout
    -0.91
    endregion
    -0.64
    TLDR
    -0.63
    bebasan
    -0.62
     mierda
    -0.62
     acceptez
    -0.61
    NegativeButton
    -0.59
     dalamnya
    -0.59
     отношению
    -0.58
     Wolfe
    -0.58
    POSITIVE LOGITS
     occasion
    3.27
     occasions
    2.94
     Occasion
    2.74
    occasion
    2.55
    Occasion
    2.44
     occas
    2.13
    occas
    2.07
     occafion
    1.98
     occa
    1.97
     occaf
    1.88
    Act Density 0.042%

    No Known Activations