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

    Neuronpedia

    INDEX
    Explanations

    words related to opinions, viewpoints, and perspectives

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a viewpoint or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ringe
    -0.69
    mpeg
    -0.69
    ring
    -0.69
    letter
    -0.69
    ubs
    -0.68
    few
    -0.68
    ACT
    -0.68
    lene
    -0.66
    949
    -0.66
    ATH
    -0.66
    POSITIVE LOGITS
     behalf
    1.32
    erous
    1.18
    etime
    0.88
    etheless
    0.86
     rooft
    0.83
    eness
    0.81
    shore
    0.80
     occasion
    0.78
    sets
    0.74
     Sundays
    0.72
    Act Density 0.142%

    No Known Activations