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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'old'

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "old."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utterstock
    -0.84
    Ĥİ
    -0.81
    atography
    -0.77
    rer
    -0.76
    rawdownloadcloneembedreportprint
    -0.75
    plementation
    -0.75
     athlet
    -0.75
    vous
    -0.74
    illation
    -0.73
    rencies
    -0.73
    POSITIVE LOGITS
     fashioned
    1.44
    rums
    0.98
    school
    0.98
    est
    0.92
    fashioned
    0.92
     standby
    0.91
     timers
    0.90
    timer
    0.82
     fart
    0.80
     school
    0.78
    Act Density 0.037%

    No Known Activations