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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positional shifts or adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Topping
    -0.45
     Foire
    -0.43
    databinding
    -0.43
     درب
    -0.42
    IsInitialized
    -0.41
    قطع
    -0.41
    toMatch
    -0.41
     geboten
    -0.41
     chio
    -0.41
     valueForKey
    -0.40
    POSITIVE LOGITS
     moved
    1.54
     shifted
    1.45
     shift
    1.43
     move
    1.37
     Moved
    1.31
    moved
    1.31
     shifting
    1.26
     Move
    1.25
     Shift
    1.23
     moving
    1.21
    Act Density 0.522%

    No Known Activations