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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and control

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    REDACTED
    -0.73
    Closure
    -0.72
    Written
    -0.70
    TION
    -0.68
    iece
    -0.68
    ilateral
    -0.68
    imp
    -0.67
    ibl
    -0.66
    grave
    -0.64
    å°Ĩ
    -0.63
    POSITIVE LOGITS
     pays
    1.02
     reap
    1.01
     accumulate
    1.00
     participates
    0.99
     participate
    0.95
     enjoy
    0.93
     populate
    0.92
     earn
    0.92
     inherit
    0.92
     regulate
    0.92
    Act Density 0.656%

    No Known Activations