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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases emphasizing "greater than" or "more than" with varying levels of strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pooja
    -0.55
    存于互联网档案馆
    -0.45
     spira
    -0.44
    AddUser
    -0.44
     hairc
    -0.43
     tour
    -0.42
     irres
    -0.42
    焦
    -0.42
     jogging
    -0.42
     kug
    -0.42
    POSITIVE LOGITS
     than
    1.49
     THAN
    1.42
    than
    1.34
    Than
    1.33
    THAN
    1.21
     Than
    1.20
     niż
    1.07
     než
    0.93
     ніж
    0.89
     decât
    0.83
    Act Density 0.150%

    No Known Activations