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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions taken together or collaboratively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    оÑĪ
    -0.08
    ียร
    -0.07
    aises
    -0.07
    ÑĤÑĥ
    -0.06
    ç·Ĵ
    -0.06
    (æľĪ
    -0.06
    andan
    -0.06
    çļĦåľ°
    -0.06
    ä»°
    -0.06
    ãĤ¤ãĥ¤
    -0.06
    POSITIVE LOGITS
     enjoy
    0.10
     see
    0.10
     get
    0.09
     learn
    0.09
     discover
    0.08
     yourself
    0.08
    learn
    0.08
    see
    0.08
     experience
    0.07
     find
    0.07
    Act Density 0.028%

    No Known Activations