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

    Neuronpedia

    INDEX
    Explanations

    phrases that instruct or signify the action of searching for something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     emerges
    -0.41
     mé
    -0.40
     diffus
    -0.39
    Fac
    -0.38
     anch
    -0.36
    UpperCase
    -0.36
    Diffusion
    -0.35
     Fait
    -0.35
    бю
    -0.35
     زی
    -0.35
    POSITIVE LOGITS
     Find
    1.52
    Find
    1.50
     Learn
    1.02
    Learn
    1.01
    Determine
    0.78
     Encuentra
    0.75
     Discover
    0.75
     Trouvez
    0.75
     Determine
    0.72
     للمعارف
    0.69
    Act Density 0.201%

    No Known Activations