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

    Neuronpedia

    INDEX
    Explanations

    concepts and phrases related to memory and reflection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owi
    -0.15
     Stra
    -0.15
    emit
    -0.15
    unk
    -0.14
    pector
    -0.14
    icana
    -0.14
    çĹ
    -0.14
     Packing
    -0.13
    porto
    -0.13
    iqueta
    -0.13
    POSITIVE LOGITS
     upper
    0.27
     foremost
    0.23
     stuck
    0.22
    lod
    0.21
    upper
    0.21
     forefront
    0.21
     lodge
    0.20
     lodged
    0.20
     weighing
    0.20
    Stick
    0.20
    Act Density 0.181%

    No Known Activations