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

    Neuronpedia

    INDEX
    Explanations

    phrases related to announcements or expressions of pleasure and satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating announcements or expressions of happiness and enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.79
    anooga
    -0.75
    ById
    -0.73
    htaking
    -0.71
     comprehension
    -0.71
    calling
    -0.68
    VERTISEMENT
    -0.67
     wills
    -0.64
    river
    -0.62
    hur
    -0.61
    POSITIVE LOGITS
     announce
    1.22
     hear
    1.05
     introduce
    1.04
     admit
    1.04
     join
    0.99
     learn
    0.98
     invite
    0.95
     see
    0.95
     receive
    0.95
     participate
    0.94
    Act Density 0.071%

    No Known Activations