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

    Neuronpedia

    INDEX
    Explanations

    phrases related to different viewpoints or attitudes

    oai_token-act-pair · gpt-3.5-turbo

    references to varying viewpoints or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liam
    -0.75
    avis
    -0.73
    cakes
    -0.72
    Interstitial
    -0.71
    nard
    -0.68
    ertodd
    -0.67
    vez
    -0.67
    nar
    -0.67
    ardy
    -0.66
    oval
    -0.65
    POSITIVE LOGITS
     perspective
    0.95
     perspectives
    0.91
     viewpoint
    0.89
     Perspective
    0.83
     viewpoints
    0.79
     views
    0.76
    spection
    0.76
     view
    0.75
     Lens
    0.71
     lens
    0.71
    Act Density 0.022%

    No Known Activations