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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate early or late timings in events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aura
    -0.17
    UTE
    -0.15
    ile
    -0.15
    ful
    -0.14
     nut
    -0.14
    aims
    -0.14
    ulf
    -0.14
     sene
    -0.14
    UIS
    -0.14
    aur
    -0.14
    POSITIVE LOGITS
    -on
    0.16
    dialogs
    0.16
     doors
    0.16
    ally
    0.15
    iggs
    0.15
     enough
    0.15
    _crop
    0.14
    -On
    0.14
    zeitig
    0.14
    кÑĤа
    0.14
    Act Density 0.031%

    No Known Activations