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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing personal viewpoints or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "opinion."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tons
    -0.75
    bridge
    -0.74
    trap
    -0.72
    mind
    -0.70
    friends
    -0.69
    bang
    -0.68
    mers
    -0.67
    enegger
    -0.67
    mable
    -0.67
    ammers
    -0.66
    POSITIVE LOGITS
    ated
    1.07
     polls
    0.96
     piece
    0.93
    atorial
    0.93
     opinions
    0.88
     opinion
    0.86
     largeDownload
    0.81
    ately
    0.79
     polling
    0.79
    atively
    0.79
    Act Density 0.037%

    No Known Activations