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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diaries or official records

    oai_token-act-pair · gpt-3.5-turbo

    references to diaries or journal entries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Quantity
    -0.70
    atche
    -0.69
    ETF
    -0.68
    Conservative
    -0.67
    VP
    -0.66
    popular
    -0.65
    Stew
    -0.63
     constitu
    -0.63
    sh
    -0.62
    umm
    -0.62
    POSITIVE LOGITS
    iary
    0.94
    iaries
    0.75
    oreal
    0.74
     confinement
    0.69
     resemblance
    0.69
    veyard
    0.67
    rarily
    0.66
    closure
    0.65
    ily
    0.64
     Alphabet
    0.62
    Act Density 0.013%

    No Known Activations