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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction or pride

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating positive announcements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hill
    -0.81
     alters
    -0.80
     modified
    -0.67
    soDeliveryDate
    -0.65
    scan
    -0.65
    imgur
    -0.64
    destruct
    -0.63
     modification
    -0.62
     modifier
    -0.61
     intellig
    -0.61
    POSITIVE LOGITS
    clus
    0.90
     welcoming
    0.79
    Brave
    0.73
    76561
    0.72
     congratulate
    0.71
    Ü
    0.69
     Fren
    0.68
     applaud
    0.68
    ¥µ
    0.67
     celebrate
    0.66
    Act Density 0.395%

    No Known Activations