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

    Neuronpedia

    INDEX
    Explanations

    references to literary works and their authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DOI
    -0.17
    eling
    -0.17
    469
    -0.17
    uce
    -0.15
    hiba
    -0.15
    posables
    -0.15
    lds
    -0.14
     Leak
    -0.14
     Loud
    -0.14
    以
    -0.14
    POSITIVE LOGITS
    ierre
    0.18
     during
    0.18
    during
    0.15
    IRROR
    0.15
     pred
    0.15
     Schwarz
    0.15
     entirely
    0.15
     around
    0.14
     originally
    0.14
    ossier
    0.14
    Act Density 0.111%

    No Known Activations