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

    Neuronpedia

    INDEX
    Explanations

    references to walls and wall-related features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.17
    elli
    -0.17
    åłĤ
    -0.16
    serter
    -0.15
    OrCreate
    -0.15
    ìľ¨
    -0.15
    yı
    -0.15
    esus
    -0.15
    fty
    -0.14
    ect
    -0.14
    POSITIVE LOGITS
    abies
    0.29
    aby
    0.27
    -mounted
    0.25
    ace
    0.22
    å£ģ
    0.20
    /window
    0.20
    owing
    0.19
    papers
    0.18
    enstein
    0.18
    aver
    0.18
    Act Density 0.029%

    No Known Activations