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

    Neuronpedia

    INDEX
    Explanations

    sentences conveying a personal experience or conversation

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation, indicating completed thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.88
     millenn
    -0.82
    ratulations
    -0.78
     unsus
    -0.78
     parachute
    -0.77
     matured
    -0.75
     transact
    -0.75
     concess
    -0.74
     fermented
    -0.74
     favourable
    -0.73
    POSITIVE LOGITS
    âĢ
    1.56
     âĢ
    1.52
     "(
    1.36
     �
    1.35
     "[
    1.34
     ``
    1.20
     "'
    1.20
     \"
    1.19
     "âĢ¦
    1.19
     Asked
    1.18
    Act Density 0.169%

    No Known Activations