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

    Neuronpedia

    INDEX
    Explanations

    ages related to people's ages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ages, specifically formatted as numerical age representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dickinson
    -0.79
     saga
    -0.75
     cipher
    -0.73
     Paradox
    -0.71
     Doom
    -0.66
     Assassin
    -0.66
     hack
    -0.65
     constellation
    -0.63
    ulhu
    -0.63
     drawer
    -0.63
    POSITIVE LOGITS
    eyed
    1.08
    year
    1.08
    degree
    1.03
    serving
    1.00
    sized
    0.99
    armed
    0.98
    duty
    0.97
    years
    0.97
    bodied
    0.96
    cand
    0.95
    Act Density 0.214%

    No Known Activations