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

    Neuronpedia

    INDEX
    Explanations

    references to expressions of support or enthusiasm

    oai_token-act-pair · gpt-3.5-turbo

    instances and variations of the word "cheer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nesota
    -0.65
    ngth
    -0.61
     intermediary
    -0.60
     Deadline
    -0.60
    amation
    -0.59
     encyclopedia
    -0.59
    course
    -0.59
     consultation
    -0.58
     Danger
    -0.58
     acquaintance
    -0.58
    POSITIVE LOGITS
    leaders
    1.43
    leader
    1.41
    leading
    1.37
    lead
    1.23
     cheer
    0.98
    fulness
    0.98
    hovah
    0.96
    fully
    0.90
    sticks
    0.89
     cheering
    0.85
    Act Density 0.037%

    No Known Activations