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

    Neuronpedia

    INDEX
    Explanations

    terms related to distinguishing or differentiating between concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     xPos
    -0.59
     kasarigan
    -0.50
     Huis
    -0.50
    Vorlage
    -0.49
    Glad
    -0.49
     prayer
    -0.48
     atto
    -0.48
    HttpPost
    -0.48
     Holliday
    -0.47
    medication
    -0.46
    POSITIVE LOGITS
     distinguish
    1.26
     differentiate
    1.21
     distingue
    1.21
     distinguishing
    1.16
     distinguishes
    1.12
     differentiates
    1.12
     distinguir
    1.12
     differentiating
    1.10
     distinguer
    1.10
     distinction
    1.06
    Act Density 0.284%

    No Known Activations