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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or novelty in offerings or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    á»ijt
    -0.21
     Actual
    -0.17
    ека
    -0.15
    ameleon
    -0.14
    emek
    -0.14
    ãĤį
    -0.14
    å½ĵ
    -0.14
    ëįĶ
    -0.14
    pard
    -0.14
    createTime
    -0.14
    POSITIVE LOGITS
     previously
    0.37
     Previously
    0.28
     elsewhere
    0.28
     before
    0.28
    seen
    0.27
     otherwise
    0.27
    Previously
    0.26
     previous
    0.26
     seen
    0.26
    -before
    0.25
    Act Density 0.086%

    No Known Activations