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

    Neuronpedia

    INDEX
    Explanations

    negative emotions and themes of resistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beyond
    -0.21
     Beyond
    -0.20
    enz
    -0.19
    illard
    -0.17
    eyond
    -0.17
     enough
    -0.16
    Beyond
    -0.15
    iset
    -0.14
     Unless
    -0.14
    iamond
    -0.14
    POSITIVE LOGITS
     nor
    0.35
    Nor
    0.29
    nor
    0.27
     Nor
    0.26
     NOR
    0.21
     EITHER
    0.19
     either
    0.18
    Either
    0.17
     Either
    0.17
     Norris
    0.17
    Act Density 0.274%

    No Known Activations