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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to environmental and political activism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.59
     en
    -0.55
    .
    -0.52
    ,
    -0.52
    ↵
    -0.48
     der
    -0.48
     (
    -0.46
     un
    -0.46
    '
    -0.45
     ex
    -0.44
    POSITIVE LOGITS
     itſelf
    1.07
     Majefty
    1.07
     purpoſe
    1.01
     ſeveral
    1.00
     Monfieur
    0.97
     pleaſure
    0.96
     houſe
    0.95
     Anſ
    0.94
     myſelf
    0.94
     Houſe
    0.94
    Act Density 0.142%

    No Known Activations