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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating various states or conditions of entities or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pus
    -0.17
     totiž
    -0.17
    hai
    -0.14
    rah
    -0.14
     Herbert
    -0.14
    654
    -0.14
    iding
    -0.14
    elerik
    -0.14
    çĩ
    -0.14
    anine
    -0.13
    POSITIVE LOGITS
     otherwise
    0.15
    eview
    0.14
    maz
    0.14
    JsonValue
    0.14
    ossa
    0.14
    .opend
    0.14
    .SizeType
    0.13
     bot
    0.13
    ched
    0.13
    abcdefghijklmnopqrstuvwxyz
    0.13
    Act Density 0.846%

    No Known Activations