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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the presence of "in" and "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sle
    -0.79
     hurled
    -0.78
     assailants
    -0.71
     aides
    -0.70
     rapists
    -0.70
     snipers
    -0.67
     partisans
    -0.66
     perpetrators
    -0.66
     torture
    -0.66
     shoved
    -0.65
    POSITIVE LOGITS
    roads
    1.12
     partnership
    1.09
     conjunction
    1.00
     Bangalore
    0.97
     India
    0.96
     Mumbai
    0.94
     Asia
    0.92
     Australia
    0.91
     Europe
    0.91
     California
    0.91
    Act Density 0.146%

    No Known Activations