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

    Neuronpedia

    INDEX
    Explanations

    statements regarding research findings and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.88
     ſche
    -0.84
     ſtate
    -0.75
     houſe
    -0.73
     ſever
    -0.73
     Reſ
    -0.73
     faſt
    -0.70
     greateſt
    -0.69
     Majefty
    -0.69
     laſt
    -0.68
    POSITIVE LOGITS
     use
    0.69
     creation
    0.63
     manufacture
    0.63
    AsUp
    0.55
    creation
    0.54
     provision
    0.50
     spread
    0.49
     development
    0.49
     hånd
    0.48
     formation
    0.48
    Act Density 0.507%

    No Known Activations