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

    Neuronpedia

    INDEX
    Explanations

    phrases related to methods and processes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     كومونز
    -0.64
    -0.55
     pris
    -0.50
    ประกอบ
    -0.46
    enuta
    -0.46
     contre
    -0.44
    人民共和国
    -0.43
    świ
    -0.42
    mbh
    -0.42
    ecio
    -0.42
    POSITIVE LOGITS
     ways
    1.64
     way
    1.50
     Ways
    1.27
     manner
    1.26
     Way
    1.18
     WAYS
    1.17
     WAY
    1.17
     maneras
    1.16
    Ways
    1.15
    Way
    1.13
    Act Density 0.329%

    No Known Activations