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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "down" and variations thereof in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.56
    لينكات
    -0.54
     femininas
    -0.52
    หวัด
    -0.49
     autorytatywna
    -0.48
    lgari
    -0.47
     dieß
    -0.47
     '\\;'
    -0.47
     budow
    -0.46
     jengibre
    -0.46
    POSITIVE LOGITS
    pour
    0.56
    sizing
    0.54
    hearted
    0.47
    stairs
    0.46
    river
    0.45
     syndrome
    0.44
    payment
    0.44
    POUR
    0.43
    queryInterface
    0.43
    stream
    0.42
    Act Density 0.142%

    No Known Activations