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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permission or authorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    allowed to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.49
    mêmes
    -0.47
     préfé
    -0.46
    endroit
    -0.45
     comuniques
    -0.45
    VolleyError
    -0.44
    opcional
    -0.42
     drôle
    -0.42
     sebaliknya
    -0.41
     Infór
    -0.40
    POSITIVE LOGITS
     fit
    0.56
    sizeCache
    0.46
     kaarangay
    0.46
     falling
    0.45
     fall
    0.44
    addContainerGap
    0.41
    ьаж
    0.41
     Plenum
    0.41
    ✨:
    0.40
     uintptr
    0.40
    Act Density 0.202%

    No Known Activations