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

    Neuronpedia

    INDEX
    Explanations

    the term "wild" and its variations, indicating a focus on wilderness and nature-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idar
    -0.17
    aurus
    -0.17
    atk
    -0.15
    .scalablytyped
    -0.15
    ception
    -0.14
    /Foundation
    -0.14
    hta
    -0.14
    stown
    -0.14
    ooke
    -0.14
    enos
    -0.14
    POSITIVE LOGITS
    erness
    0.29
    ernes
    0.23
    flowers
    0.21
    er
    0.21
    cat
    0.21
    fires
    0.20
    -eyed
    0.19
    flower
    0.19
    ridge
    0.18
    ness
    0.18
    Act Density 0.017%

    No Known Activations