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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their related actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of placing or handling objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     understatement
    -0.68
    roads
    -0.61
     Kelley
    -0.60
    ofer
    -0.56
     Founding
    -0.55
     Miguel
    -0.55
     Polk
    -0.55
     Cars
    -0.55
     Paso
    -0.55
     Balt
    -0.54
    POSITIVE LOGITS
    anwhile
    0.91
    alian
    0.85
    atic
    0.83
     accordingly
    0.82
     onto
    0.79
    ividual
    0.73
     into
    0.73
     overboard
    0.73
    self
    0.72
    essage
    0.70
    Act Density 0.147%

    No Known Activations