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

    Neuronpedia

    INDEX
    Explanations

    words related to wild nature

    oai_token-act-pair · gpt-3.5-turbo

    references to wilderness or wildness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "wild"

    Explanation Uploaded by User
    New Auto-Interp
    Negative Logits
    uyomi
    -0.91
    adr
    -0.83
    rators
    -0.79
    akeru
    -0.78
    oute
    -0.78
    aminer
    -0.77
    uters
    -0.75
    berus
    -0.75
    adian
    -0.74
    rael
    -0.72
    POSITIVE LOGITS
    erness
    1.29
    lings
    1.03
    flower
    0.97
    cat
    0.92
    fire
    0.85
    wild
    0.84
    er
    0.83
    ness
    0.83
    est
    0.81
    abouts
    0.81
    Act Density 0.020%

    No Known Activations