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

    Neuronpedia

    INDEX
    Explanations

    abbreviations in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "abbreviate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LOAD
    -0.72
    isting
    -0.71
     Jiang
    -0.70
     Zheng
    -0.69
    oop
    -0.68
    zai
    -0.67
     Pascal
    -0.66
    Bomb
    -0.66
    USH
    -0.66
    Jet
    -0.65
    POSITIVE LOGITS
     abbrevi
    1.32
     abbre
    1.28
    dayName
    0.80
     understatement
    0.79
    ĸļ
    0.75
     gauge
    0.74
    aucas
    0.73
     exha
    0.72
    abama
    0.70
    roit
    0.70
    Act Density 0.001%

    No Known Activations