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

    Neuronpedia

    INDEX
    Explanations

    references to specific events or phenomena within a contextual framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.35
    ستاگرام
    -0.35
     Италијани
    -0.34
     andata
    -0.33
    lahraga
    -0.33
     zpě
    -0.32
    spesies
    -0.31
     invokingState
    -0.30
     auguri
    -0.30
    phins
    -0.30
    POSITIVE LOGITS
     trick
    1.05
     tricks
    1.00
     Trick
    0.90
     magicians
    0.85
    trick
    0.84
     magician
    0.82
     Tricks
    0.81
    Trick
    0.75
     illusion
    0.74
     magic
    0.73
    Act Density 0.181%

    No Known Activations