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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing pride or emphasis on achievements

    oai_token-act-pair · gpt-3.5-turbo

    instances of boasting or bragging about achievements or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Solution
    -0.79
    olin
    -0.79
    umi
    -0.74
     affected
    -0.73
    Issue
    -0.72
    fix
    -0.71
    amin
    -0.68
     Causes
    -0.65
    ents
    -0.64
     invalid
    -0.64
    POSITIVE LOGITS
     boast
    3.16
     boasting
    2.94
     boasts
    2.90
     boasted
    2.85
     bragging
    2.10
     proudly
    1.27
     proud
    1.15
     touting
    1.11
     promises
    1.10
     touted
    1.07
    Act Density 0.020%

    No Known Activations