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

    Neuronpedia

    INDEX
    Explanations

    references to specific organizations, reports, or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.88
     ſever
    -0.85
     houſe
    -0.82
     themſelves
    -0.80
     ſtre
    -0.78
     faſt
    -0.75
     ſtate
    -0.75
     leſs
    -0.75
     deſt
    -0.75
     reaſon
    -0.75
    POSITIVE LOGITS
    findpost
    0.59
    Démographie
    0.50
     nakalista
    0.44
    urlencoded
    0.40
     shea
    0.39
     gmina
    0.38
    isContained
    0.37
    …”
    0.37
     veer
    0.36
     cop
    0.36
    Act Density 0.262%

    No Known Activations