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

    Neuronpedia

    INDEX
    Explanations

    references to visual representations or imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kowski
    -0.19
    neck
    -0.19
    water
    -0.16
    /fast
    -0.16
    uche
    -0.15
    chan
    -0.15
    itzer
    -0.15
    ibs
    -0.14
    pper
    -0.14
    ly
    -0.14
    POSITIVE LOGITS
    ores
    0.15
    oft
    0.15
    yen
    0.14
    askell
    0.14
    auss
    0.14
    æĪ
    0.14
    EAR
    0.14
    .theme
    0.14
    922
    0.14
    Ļ¨
    0.14
    Act Density 0.031%

    No Known Activations