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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by a verb indicating a change in perspective or opinion

    oai_token-act-pair · gpt-3.5-turbo

    references to changes in personal or subjective perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.70
    cade
    -0.64
    oaded
    -0.62
    ulhu
    -0.61
    Magikarp
    -0.61
    ccoli
    -0.60
    Dragon
    -0.58
    Hour
    -0.58
    INFO
    -0.57
    NetMessage
    -0.57
    POSITIVE LOGITS
     fortunes
    0.87
     radically
    0.79
     drastically
    0.77
    emort
    0.73
    ieties
    0.72
     habits
    0.71
     diapers
    0.71
     dramatically
    0.71
     fundamentally
    0.67
    foundland
    0.66
    Act Density 0.170%

    No Known Activations