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

    Neuronpedia

    INDEX
    Explanations

    phrases related to public announcements or introductions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unveil" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unker
    -0.76
    MQ
    -0.74
     coli
    -0.69
    oling
    -0.63
    osate
    -0.63
     saline
    -0.61
    avery
    -0.61
     overfl
    -0.61
    aunder
    -0.60
     Rutherford
    -0.60
    POSITIVE LOGITS
     unveil
    0.94
     unveiled
    0.92
     unveiling
    0.89
    éĹĺ
    0.81
    nesday
    0.79
    æ©
    0.76
     displays
    0.71
     announcements
    0.70
     showc
    0.68
    announced
    0.68
    Act Density 0.025%

    No Known Activations