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

    Neuronpedia

    INDEX
    Explanations

    phrases describing user-friendly features and functionalities of devices, particularly regarding their ease of use and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erif
    -0.15
    undi
    -0.15
    iani
    -0.15
    ector
    -0.14
    iku
    -0.14
    еÑĢÑĤи
    -0.14
    ensi
    -0.13
     Point
    -0.13
     Ramp
    -0.13
    eliac
    -0.13
    POSITIVE LOGITS
     hands
    0.28
     Hands
    0.25
    hands
    0.23
    Hands
    0.23
     distraction
    0.21
     distractions
    0.21
     distracted
    0.19
     multit
    0.18
    _while
    0.18
    HAND
    0.17
    Act Density 0.073%

    No Known Activations