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

    Neuronpedia

    INDEX
    Explanations

    adjectives that denote significant impact or notable characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ://{
    -0.16
    allet
    -0.14
    ér
    -0.14
    rire
    -0.14
    ailles
    -0.14
    elles
    -0.14
    allen
    -0.14
    á»ijt
    -0.13
    ajs
    -0.13
     favorite
    -0.13
    POSITIVE LOGITS
    yet
    0.24
     yet
    0.24
    -ever
    0.24
     imaginable
    0.23
     EVER
    0.23
    Yet
    0.21
     ever
    0.21
     possible
    0.20
    ever
    0.20
    possible
    0.20
    Act Density 0.079%

    No Known Activations