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

    Neuronpedia

    INDEX
    Explanations

    scientific research and methodologies related to studying specific variables or phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Acro
    -0.53
     söyle
    -0.52
    gi
    -0.52
     roll
    -0.51
     dupla
    -0.51
     surpre
    -0.51
    ti
    -0.51
    !
    -0.50
    **
    -0.49
      
    -0.49
    POSITIVE LOGITS
    studied
    1.32
     studied
    1.24
     Studied
    1.23
     studying
    1.22
     Studying
    1.19
     analysing
    1.19
     examining
    1.16
    Studying
    1.13
     examine
    1.13
     étudié
    1.12
    Act Density 0.515%

    No Known Activations