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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific individual's injury or absence in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.62
    ranslated
    -0.57
    hoeddwyd
    -0.53
    AsUp
    -0.52
     ngan
    -0.52
     van
    -0.50
    Дереккөздер
    -0.50
     <=",
    -0.46
    Abitanti
    -0.45
    letar
    -0.45
    POSITIVE LOGITS
     myſelf
    0.83
     pleaſure
    0.78
    
    0.76
     itſelf
    0.76
     raiſ
    0.74
     Monfieur
    0.72
     themſelves
    0.72
     ſever
    0.72
     houſe
    0.71
     ſtre
    0.70
    Act Density 0.164%

    No Known Activations