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

    Neuronpedia

    INDEX
    Explanations

    percentage expressions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    percentages and statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ©
    -0.73
     Leilan
    -0.72
    ITED
    -0.69
     Polo
    -0.68
     GOODMAN
    -0.67
    arium
    -0.66
     Fargo
    -0.64
    XT
    -0.63
    achine
    -0.63
     Sieg
    -0.63
    POSITIVE LOGITS
     capita
    1.27
    tains
    0.99
    uvian
    0.98
     cent
    0.97
    missive
    0.95
    secution
    0.94
    ishable
    0.94
    secut
    0.93
    manent
    0.89
    ience
    0.88
    Act Density 0.026%

    No Known Activations