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

    Neuronpedia

    INDEX
    Explanations

    elements associated with regular expressions and their syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     houſe
    -0.94
     uſe
    -0.88
     Houſe
    -0.88
     themſelves
    -0.87
     purpoſe
    -0.83
     faſt
    -0.82
     pleaſure
    -0.81
     myſelf
    -0.78
     Commencez
    -0.78
    =$?
    -0.77
    POSITIVE LOGITS
    (@"
    0.82
     @"
    0.81
    ("""
    0.74
     Pingback
    0.58
     /\.
    0.58
    :@"
    0.57
    <em>
    0.56
     “
    0.56
    است
    0.55
     "
    0.55
    Act Density 0.067%

    No Known Activations