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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    º
    -0.17
    empo
    -0.15
    ucas
    -0.14
    емо
    -0.14
    andro
    -0.14
    unan
    -0.14
    æĺĵ
    -0.13
    çĸĨ
    -0.13
     unseen
    -0.13
    andy
    -0.13
    POSITIVE LOGITS
     crypt
    0.29
     simply
    0.26
     vague
    0.23
    crypt
    0.23
     nothing
    0.22
     simplement
    0.21
     merely
    0.21
    Crypt
    0.19
     Crypt
    0.19
     only
    0.18
    Act Density 0.139%

    No Known Activations