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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal life

    oai_token-act-pair · gpt-3.5-turbo

    references to aspects of personal life and everyday living

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oug
    -0.84
    sonian
    -0.79
    atchewan
    -0.75
    ractive
    -0.74
    orney
    -0.73
    ypes
    -0.72
    ovi
    -0.71
    aye
    -0.71
    elfth
    -0.70
     DEFENSE
    -0.70
    POSITIVE LOGITS
     expectancy
    0.93
    guards
    0.87
    guard
    0.83
    forms
    0.81
    boat
    0.77
    blood
    0.76
     vic
    0.74
    boats
    0.74
    liness
    0.74
    styles
    0.72
    Act Density 0.045%

    No Known Activations