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

    Neuronpedia

    INDEX
    Explanations

    specific measures and observations related to cognitive performance and memory enhancements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.08
    2:0.20
    3:0.04
    4:0.02
    5:0.03
    6:0.04
    7:0.07
    8:0.04
    9:0.03
    10:0.31
    11:0.03
    Negative Logits
    ulence
    -2.35
    Priv
    -2.25
     cracks
    -2.16
     Sack
    -2.15
     rentals
    -2.06
    Sensor
    -2.06
    OY
    -2.06
    ulent
    -1.96
     sensors
    -1.94
    hetto
    -1.94
    POSITIVE LOGITS
    follow
    4.07
     followed
    3.20
     Follow
    3.17
     follow
    3.13
     follows
    2.65
     following
    2.64
     Following
    2.54
     adhere
    2.40
    vati
    2.37
     adherent
    2.34
    Act Density 0.001%

    No Known Activations