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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of characters and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    
    -0.90
     виправивши
    -0.81
    ſelves
    -0.80
     autorytatywna
    -0.79
     purpoſe
    -0.79
     houſe
    -0.77
    ſelf
    -0.77
     varandra
    -0.77
     themſelves
    -0.76
     ExecuteAsync
    -0.75
    POSITIVE LOGITS
     looked
    0.58
     chuckled
    0.52
     finally
    0.52
     smiled
    0.51
     regardé
    0.50
     had
    0.50
     put
    0.49
     sighed
    0.49
     wondered
    0.49
     went
    0.48
    Act Density 0.099%

    No Known Activations