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

    Neuronpedia

    INDEX
    Explanations

    words related to copying, imitating, or replicating

    oai_token-act-pair · gpt-3.5-turbo

    terms related to mimicking or imitating actions or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endale
    -0.71
    nut
    -0.71
    Frag
    -0.66
    band
    -0.65
    stones
    -0.65
    rich
    -0.65
    starter
    -0.64
    dies
    -0.64
    asse
    -0.63
    stone
    -0.63
    POSITIVE LOGITS
     likeness
    0.80
    natureconservancy
    0.78
    iliar
    0.75
     emulate
    0.74
    lihood
    0.71
     replicate
    0.67
     imitate
    0.66
     greatness
    0.62
    reality
    0.62
     Mara
    0.60
    Act Density 0.063%

    No Known Activations