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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating enrollment or participation in programs or courses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.07
    3:0.19
    4:0.04
    5:0.04
    6:0.05
    7:0.12
    8:0.06
    9:0.16
    10:0.07
    11:0.10
    Negative Logits
     brittle
    -1.21
    acan
    -1.20
    rescent
    -1.18
    tsy
    -1.13
    osaurus
    -1.11
    rait
    -1.11
    ndra
    -1.10
     symmetry
    -1.09
     shine
    -1.07
     silhouette
    -1.07
    POSITIVE LOGITS
     WRITE
    1.34
     dues
    1.23
    Guest
    1.16
     Bonds
    1.13
     voucher
    1.07
     Private
    1.07
     enrolled
    1.05
     Consent
    1.05
    Cook
    1.04
    Madison
    1.04
    Act Density 0.003%

    No Known Activations