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

    Neuronpedia

    INDEX
    Explanations

    announcements or declarations made by entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "announced."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cling
    -0.65
     bias
    -0.64
    Norm
    -0.63
    Value
    -0.62
     temper
    -0.61
    value
    -0.61
    ylene
    -0.61
    arton
    -0.61
     abusers
    -0.60
    Values
    -0.60
    POSITIVE LOGITS
     announced
    3.26
     announces
    2.10
    announced
    2.09
     unveiled
    2.08
     announce
    2.08
     announcement
    1.86
     announcing
    1.75
     announcements
    1.72
     disclosed
    1.61
     declared
    1.58
    Act Density 0.025%

    No Known Activations