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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating resistance to change or absence of significant impact

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a lack of change or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alian
    -0.72
    multiple
    -0.63
    abouts
    -0.63
    aran
    -0.63
     intertw
    -0.62
     maneu
    -0.61
     indo
    -0.60
    jan
    -0.59
     Courtesy
    -0.58
    ortment
    -0.56
    POSITIVE LOGITS
     anymore
    1.35
     nor
    1.34
     whatsoever
    1.16
     anything
    1.15
    nor
    1.04
     anybody
    1.01
     slightest
    1.00
     any
    0.97
     either
    0.95
     anytime
    0.89
    Act Density 0.304%

    No Known Activations