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

    Neuronpedia

    INDEX
    Explanations

    terms related to distinguishing or differentiating between different options or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gedicht
    -0.51
     xPos
    -0.50
     áll
    -0.49
    İK
    -0.47
     atto
    -0.47
    itzende
    -0.46
    expires
    -0.45
     god
    -0.43
    oris
    -0.43
    ALLENGES
    -0.43
    POSITIVE LOGITS
     distinguish
    1.22
     differentiate
    1.19
     distinguishing
    1.19
     distingue
    1.12
     differentiates
    1.10
     differentiating
    1.08
     distinguir
    1.08
     distinguishes
    1.07
     distinction
    1.07
    distingu
    1.02
    Act Density 0.385%

    No Known Activations