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

    Neuronpedia

    INDEX
    Explanations

    programming-related syntax and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wright
    -0.15
     Compression
    -0.15
    ooled
    -0.14
    ans
    -0.14
    atsby
    -0.14
     Assembly
    -0.14
     herk
    -0.14
     آس
    -0.14
    urses
    -0.14
    758
    -0.14
    POSITIVE LOGITS
     iron
    0.32
     Polymer
    0.32
    iron
    0.32
     polymer
    0.31
     paper
    0.30
     Iron
    0.30
    Iron
    0.30
     Paper
    0.27
    paper
    0.27
    IRON
    0.27
    Act Density 0.026%

    No Known Activations