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

    Neuronpedia

    INDEX
    Explanations

    titles or references to various shows or programs, especially those related to morning or daily shows, as well as terms related to old-fashioned observation and concerns about different topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to news programs and cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otom
    -0.80
    udic
    -0.76
    615
    -0.73
    utor
    -0.73
    çīĪ
    -0.70
    sbm
    -0.69
     balcon
    -0.68
     Fernand
    -0.67
    USS
    -0.66
    ural
    -0.65
    POSITIVE LOGITS
     luck
    0.81
     outweigh
    0.79
     Samar
    0.77
    bye
    0.77
    ornings
    0.74
     outwe
    0.73
     Smile
    0.68
     Luck
    0.68
    nered
    0.67
     Hunting
    0.66
    Act Density 0.224%

    No Known Activations