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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "space" related to context or usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.94
     zelve
    -0.91
     hydrauli
    -0.89
    (!__
    -0.87
     défaite
    -0.87
     ainfi
    -0.86
     aveug
    -0.85
    VolleyError
    -0.85
     themſelves
    -0.85
    quelles
    -0.84
    POSITIVE LOGITS
     space
    2.45
     spaces
    2.27
     Space
    2.26
     SPACE
    2.16
    space
    2.13
    Space
    2.13
     Spaces
    2.05
    Spaces
    2.04
    SPACE
    2.00
    spaces
    1.97
    Act Density 0.041%

    No Known Activations