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

    Neuronpedia

    INDEX
    Explanations

    words related to estimates, estimations, and imprecise quantifications

    oai_token-act-pair · gpt-3.5-turbo

    words related to estimation and quantification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spr
    -0.77
    Bloom
    -0.71
     daring
    -0.68
     refreshing
    -0.63
     appealed
    -0.62
     sidel
    -0.62
    shall
    -0.62
    inis
    -0.62
    Else
    -0.61
     Kah
    -0.60
    POSITIVE LOGITS
    imate
    1.40
    imation
    1.00
    oice
    0.94
    imating
    0.89
    imated
    0.88
    imates
    0.87
    ction
    0.82
    andum
    0.81
    itri
    0.80
    lation
    0.77
    Act Density 0.012%

    No Known Activations