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

    Neuronpedia

    INDEX
    Explanations

    the word "same" followed by additional contextual information

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "same" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĵĺ
    -0.79
    phasis
    -0.76
    erest
    -0.76
    skirts
    -0.74
    better
    -0.73
    hyde
    -0.70
    ifest
    -0.68
    acus
    -0.68
    Orderable
    -0.67
    arest
    -0.66
    POSITIVE LOGITS
     vein
    1.05
     day
    0.93
     month
    0.92
     timeframe
    0.91
     exact
    0.87
     week
    0.86
     thing
    0.82
     year
    0.82
     weekend
    0.81
     theme
    0.78
    Act Density 0.035%

    No Known Activations