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

    Neuronpedia

    INDEX
    Explanations

    specific names of organizations, characters, and elements related to media and fictional universes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Haf
    -1.08
     Huf
    -1.04
    Taf
    -0.97
     Bof
    -0.92
     Tof
    -0.91
     pof
    -0.90
    Coff
    -0.90
     Sif
    -0.90
     DIF
    -0.90
     Nef
    -0.89
    POSITIVE LOGITS
     Jann
    0.87
    FileChooser
    0.84
    
    0.78
     Wür
    0.78
     Juga
    0.71
    澡
    0.71
     Schatz
    0.69
     Liar
    0.69
     Iri
    0.68
     Ebers
    0.67
    Act Density 2.070%

    No Known Activations