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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to percentages

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating statistical percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leilan
    -0.79
    ESCO
    -0.71
     Polo
    -0.67
     Xer
    -0.67
     Pegasus
    -0.65
    XT
    -0.64
    ITED
    -0.64
     Blank
    -0.62
    Friends
    -0.62
     QR
    -0.60
    POSITIVE LOGITS
     capita
    1.13
    uvian
    0.99
    tains
    0.97
    secut
    0.96
     cent
    0.95
    missive
    0.93
    versely
    0.90
    secution
    0.90
    malink
    0.90
    ience
    0.87
    Act Density 0.024%

    No Known Activations