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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating denial or claims of knowledge about events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -mf
    -0.17
    obus
    -0.16
    ric
    -0.15
    lenen
    -0.15
    æĺŃ
    -0.14
    lest
    -0.14
    itchens
    -0.14
    clr
    -0.14
    λη
    -0.14
    immel
    -0.14
    POSITIVE LOGITS
    å·±
    0.17
    baugh
    0.15
    anou
    0.15
     hacking
    0.14
    ÙĪاÙĨ
    0.14
    ÏħÏĥ
    0.14
     Mercer
    0.14
     relief
    0.14
    uler
    0.13
    ordan
    0.13
    Act Density 0.068%

    No Known Activations