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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating motivations or reasons for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atar
    -0.20
     neutral
    -0.16
     kn
    -0.15
    atr
    -0.14
    atcher
    -0.14
     NotImplementedError
    -0.14
    ebra
    -0.14
    igure
    -0.14
    518
    -0.14
    porto
    -0.14
    POSITIVE LOGITS
    GMEM
    0.19
     defaultManager
    0.16
    _Tick
    0.16
    @update
    0.15
    OKIE
    0.15
    PageRoute
    0.15
    infer
    0.15
    inking
    0.15
    otionEvent
    0.15
     Mage
    0.14
    Act Density 0.188%

    No Known Activations