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

    Neuronpedia

    INDEX
    Explanations

    research-related language indicating prior studies and findings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    
    -0.57
    kháu
    -0.56
    TagMode
    -0.54
     Roskov
    -0.54
    شهاد
    -0.52
    เย
    -0.51
    ardos
    -0.50
    AutoresizingMask
    -0.49
    NVIC
    -0.48
     encor
    -0.47
    POSITIVE LOGITS
    ViewImports
    0.72
     undersigned
    0.61
     précédents
    0.60
     précédentes
    0.59
     myself
    0.57
    myself
    0.57
    unpublished
    0.56
     précédemment
    0.56
     librement
    0.53
     namin
    0.52
    Act Density 0.405%

    No Known Activations