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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating ongoing changes or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     erect
    -0.18
     rapid
    -0.17
     abort
    -0.16
     demol
    -0.16
     reversing
    -0.16
     abol
    -0.16
     restoration
    -0.16
     undo
    -0.16
     reversal
    -0.15
     Rapid
    -0.15
    POSITIVE LOGITS
     modified
    0.36
    modified
    0.32
     changed
    0.32
     adjusted
    0.32
     expanded
    0.32
     altered
    0.32
     enhanced
    0.31
     extended
    0.31
     improved
    0.31
    Modified
    0.29
    Act Density 0.349%

    No Known Activations