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

    Neuronpedia

    INDEX
    Explanations

    references to walls or structures in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zelf
    -0.17
    eka
    -0.16
    /errors
    -0.16
    ois
    -0.15
    rana
    -0.15
    esus
    -0.15
    elli
    -0.15
    sak
    -0.15
    OrCreate
    -0.15
    oga
    -0.15
    POSITIVE LOGITS
    abies
    0.26
    aby
    0.25
    flower
    0.24
    -mounted
    0.24
    owing
    0.23
    /window
    0.23
    ace
    0.22
    aver
    0.21
    papers
    0.21
    paper
    0.21
    Act Density 0.034%

    No Known Activations