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

    Neuronpedia

    INDEX
    Explanations

    phrases related to admiration or giving praise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to naval ranks and admirals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ARB
    -0.73
    DAY
    -0.71
    THER
    -0.69
    staking
    -0.67
    DragonMagazine
    -0.66
     Palmer
    -0.65
    meal
    -0.65
    ters
    -0.65
    BOX
    -0.64
    turn
    -0.63
    POSITIVE LOGITS
    ittance
    1.28
    ixture
    1.12
    ixed
    1.09
    iral
    1.06
    igration
    0.93
    ably
    0.88
    opol
    0.88
    igmat
    0.86
    antly
    0.86
    ittees
    0.85
    Act Density 0.019%

    No Known Activations