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

    Neuronpedia

    INDEX
    Explanations

    the word "floor" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -1.00
      
    -0.92
     "
    -0.84
     (
    -0.82
     S
    -0.77
    ↵
    -0.77
     The
    -0.77
    ↵↵
    -0.74
     T
    -0.73
     M
    -0.71
    POSITIVE LOGITS
     Efq
    2.13
     myſelf
    2.06
     Jefus
    1.99
     Eſ
    1.94
     Majefty
    1.94
     becauſe
    1.93
     Monfieur
    1.92
     Theſe
    1.89
     Houſe
    1.88
     itſelf
    1.85
    Act Density 0.146%

    No Known Activations