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

    Neuronpedia

    INDEX
    Explanations

    SELECT statements or keywords often used in computer programming and database querying

    oai_token-act-pair · gpt-3.5-turbo

    references to "select" or selection processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nerv
    -0.72
    FORE
    -0.71
    STD
    -0.70
    loo
    -0.68
    ipple
    -0.66
    ijk
    -0.66
    abwe
    -0.65
    peria
    -0.64
    chief
    -0.64
    nz
    -0.62
    POSITIVE LOGITS
    ivity
    1.26
    ively
    1.08
    ives
    0.97
    ivities
    0.86
    prising
    0.84
    cuts
    0.83
    inations
    0.80
    ions
    0.77
    orate
    0.76
    ive
    0.74
    Act Density 0.028%

    No Known Activations