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

    Neuronpedia

    INDEX
    Explanations

    references to visual elements or visual representation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ordini
    -0.66
    pede
    -0.62
     pomeriggio
    -0.61
    latte
    -0.61
    ubarak
    -0.59
     @"/
    -0.59
    abetes
    -0.57
     trovi
    -0.57
     AMT
    -0.55
    ineno
    -0.55
    POSITIVE LOGITS
    VISUAL
    1.33
     VISUAL
    1.24
     visual
    1.20
     VIS
    1.19
     Vis
    1.19
     Visser
    1.18
     Visual
    1.17
    visual
    1.15
     visuals
    1.10
     visuel
    1.08
    Act Density 0.129%

    No Known Activations