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

    Neuronpedia

    INDEX
    Explanations

    references to statistical or mathematical notation relating to quantities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.10
     Monfieur
    -1.02
    -1.00
     pleaſure
    -0.99
     Efq
    -0.96
     themſelves
    -0.93
     uſed
    -0.93
     becauſe
    -0.92
     photolibrary
    -0.91
    principalTable
    -0.90
    POSITIVE LOGITS
     and
    0.40
     Ar
    0.40
    ,
    0.40
    -
    0.39
     
    0.39
    .
    0.39
    ↵↵
    0.37
    iorgio
    0.36
    ódź
    0.36
    pass
    0.36
    Act Density 0.000%

    No Known Activations