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

    Neuronpedia

    INDEX
    Explanations

    references to "wild" and "wilderness" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dem
    -0.16
    atk
    -0.16
    plist
    -0.16
    aurus
    -0.16
    ception
    -0.15
    .scalablytyped
    -0.14
    ovatel
    -0.14
    rze
    -0.14
     Madden
    -0.14
    .googleapis
    -0.14
    POSITIVE LOGITS
    erness
    0.30
    cat
    0.26
    er
    0.25
    flowers
    0.25
    flower
    0.24
    ernes
    0.23
    cards
    0.23
    ness
    0.21
    fires
    0.21
    life
    0.20
    Act Density 0.015%

    No Known Activations