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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or behaviors of other people

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and permissions involving others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Playoff
    -0.76
    enegger
    -0.69
     Unle
    -0.67
    irst
    -0.67
     finale
    -0.65
     Tycoon
    -0.64
     Notting
    -0.64
     Highlights
    -0.62
     Appropri
    -0.61
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
    POSITIVE LOGITS
    worldly
    0.81
    ioch
    0.80
    iris
    0.78
    inois
    0.75
    than
    0.75
     faiths
    0.75
     expend
    0.72
    aband
    0.70
     perspectives
    0.70
     besides
    0.70
    Act Density 0.450%

    No Known Activations