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

    Neuronpedia

    INDEX
    Explanations

    specific words and phrases that indicate thresholds or criteria in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lately
    -0.17
     ÙĨس
    -0.16
    latest
    -0.14
     latest
    -0.14
    даÑĤ
    -0.14
    Confirmed
    -0.14
    ä¸Ģ人
    -0.13
    uddenly
    -0.13
    æľĢè¿ij
    -0.13
    337
    -0.13
    POSITIVE LOGITS
     Christmas
    0.17
     Everywhere
    0.16
    Christmas
    0.16
     friends
    0.16
     Thanksgiving
    0.15
     fall
    0.15
     exactly
    0.15
    eldorf
    0.15
     holiday
    0.15
     circumstances
    0.14
    Act Density 0.037%

    No Known Activations