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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to things that are untamed or unrestrained

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wild."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uyomi
    -0.90
    adr
    -0.79
    rators
    -0.76
    alach
    -0.76
    akeru
    -0.75
    aminer
    -0.74
    adian
    -0.74
    velength
    -0.73
    rael
    -0.71
    ablishment
    -0.70
    POSITIVE LOGITS
    erness
    1.29
    lings
    1.00
    flower
    0.91
    wild
    0.88
    cat
    0.88
    er
    0.85
    fire
    0.82
    WOOD
    0.79
    est
    0.78
    spe
    0.77
    Act Density 0.015%

    No Known Activations