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

    Neuronpedia

    INDEX
    Explanations

    references to space usage or management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -1.16
     themſelves
    -1.06
     Majefty
    -1.03
    OGND
    -1.02
     pleaſure
    -0.99
     myſelf
    -0.98
     zelve
    -0.97
     himſelf
    -0.96
    __":
    -0.95
    UnusedPrivate
    -0.94
    POSITIVE LOGITS
     space
    1.72
     spaces
    1.63
     Space
    1.63
     SPACE
    1.55
    Spaces
    1.50
     Spaces
    1.50
    Space
    1.48
    SPACE
    1.45
    space
    1.44
    spaces
    1.37
    Act Density 0.041%

    No Known Activations