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

    Neuronpedia

    INDEX
    Explanations

    formal descriptions of study objectives and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -1.01
     Monfieur
    -0.91
     myſelf
    -0.91
     Theſe
    -0.84
     leaſt
    -0.83
     Efq
    -0.83
    ſelf
    -0.80
    ^(@)
    -0.78
     $_"
    -0.78
     ་་
    -0.78
    POSITIVE LOGITS
     paper
    1.06
     this
    1.01
     study
    1.00
    今回は
    0.95
     present
    0.89
    paper
    0.86
    this
    0.84
    本文
    0.83
    本
    0.83
     research
    0.82
    Act Density 1.138%

    No Known Activations