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

    Neuronpedia

    INDEX
    Explanations

    phrases that suggest coming out, whether in a literal or metaphorical sense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("/{
    -0.56
     quelles
    -0.55
    :✨
    -0.55
    arakhand
    -0.52
     précieux
    -0.52
    ůli
    -0.51
    ญิง
    -0.50
    arean
    -0.50
    ercizi
    -0.50
     PER
    -0.49
    POSITIVE LOGITS
     emerges
    0.74
     emerge
    0.68
     LoggerFactory
    0.65
    Releases
    0.64
     emerged
    0.64
    ออกมา
    0.63
     favorably
    0.62
     APPE
    0.60
     Trident
    0.60
     Giri
    0.59
    Act Density 0.079%

    No Known Activations