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

    Neuronpedia

    INDEX
    Explanations

    negations and expressions of rejection or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    384
    -0.16
    etri
    -0.16
     Banc
    -0.15
    tej
    -0.15
    ucci
    -0.15
    alm
    -0.15
    ÙĬات
    -0.14
    ï¼ĪæĺŃåĴĮ
    -0.14
    utz
    -0.14
    lobby
    -0.14
    POSITIVE LOGITS
     necessarily
    0.16
    287
    0.14
    riger
    0.14
    [@
    0.14
     bare
    0.14
    LEAR
    0.14
    -original
    0.13
     Universities
    0.13
     Alternative
    0.13
     Tw
    0.13
    Act Density 0.039%

    No Known Activations