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

    Neuronpedia

    INDEX
    Explanations

    phrases related to obtaining something or achieving a goal

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "get" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lies
    -0.66
     cardinal
    -0.66
     Inher
    -0.64
    iege
    -0.63
     Tanz
    -0.62
     experiment
    -0.60
    NESS
    -0.59
     Duty
    -0.58
     Wonders
    -0.58
     Archdemon
    -0.58
    POSITIVE LOGITS
     rid
    1.56
     acquainted
    1.00
     away
    0.90
    bent
    0.88
    TING
    0.87
     distracted
    0.86
     Started
    0.84
    away
    0.84
    cloneembedreportprint
    0.83
     INTO
    0.80
    Act Density 0.121%

    No Known Activations