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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.05
     Majefty
    -1.03
     purpoſe
    -1.02
     Jefus
    -1.01
     Cæsar
    -1.01
     uſed
    -0.99
     itſelf
    -0.99
     themſelves
    -0.95
     houſe
    -0.95
     Monfieur
    -0.95
    POSITIVE LOGITS
    ↵↵
    0.75
    .
    0.54
     P
    0.50
     '
    0.48
     C
    0.47
    ='';
    0.47
    ViewFeatures
    0.47
     Mach
    0.46
     :
    0.46
    ↵↵↵↵
    0.45
    Act Density 0.194%

    No Known Activations