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

    Neuronpedia

    INDEX
    Explanations

    personal names ending in 'der'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "der."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¥
    -0.60
     allotted
    -0.60
     lunch
    -0.59
     gardens
    -0.58
     Batt
    -0.57
     smartphones
    -0.57
     meals
    -0.57
     spent
    -0.57
     devoted
    -0.55
     surveyed
    -0.55
    POSITIVE LOGITS
    der
    4.84
    DER
    1.89
    ding
    1.53
    Der
    1.36
    ded
    1.35
    die
    1.35
    dy
    1.33
    den
    1.33
    dar
    1.31
    du
    1.24
    Act Density 0.015%

    No Known Activations