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

    Neuronpedia

    INDEX
    Explanations

    specific names and references related to authors and academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Composable
    -1.03
     <<<<<<<<<<<<<<
    -0.94
    Portale
    -0.83
     Waffle
    -0.83
     Anson
    -0.81
    andam
    -0.77
    Ske
    -0.75
    Anson
    -0.74
     protocole
    -0.74
    
    -0.73
    POSITIVE LOGITS
     Azz
    0.93
     Taz
    0.90
    ########.
    0.89
     Mox
    0.86
     Trix
    0.86
     Daz
    0.85
     Kiz
    0.85
    BoxShadow
    0.85
     taz
    0.84
     Bux
    0.84
    Act Density 1.820%

    No Known Activations