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

    Neuronpedia

    INDEX
    Explanations

    announcements or declarations of events or achievements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate announcements or news releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usra
    -0.81
    igion
    -0.78
    irit
    -0.73
    thing
    -0.72
     tended
    -0.71
    pill
    -0.71
    cius
    -0.70
    udge
    -0.70
    beh
    -0.69
     heck
    -0.69
    POSITIVE LOGITS
     partnerships
    0.91
     partnership
    0.86
     Selected
    0.76
     Remastered
    0.75
    âĦ¢:
    0.75
     Releases
    0.74
     Franchise
    0.74
     ANN
    0.73
     Congratulations
    0.71
     FANTASY
    0.70
    Act Density 0.232%

    No Known Activations