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

    Neuronpedia

    INDEX
    Explanations

    references to action verbs related to movement or progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.07
    2:0.08
    3:0.09
    4:0.09
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
     eligibility
    -2.35
     ACT
    -2.29
     passwords
    -2.16
    IDs
    -2.13
     Visa
    -2.13
     registration
    -2.12
     waivers
    -2.10
     registrations
    -2.10
     ratings
    -2.06
    WHO
    -2.05
    POSITIVE LOGITS
    arte
    2.49
    entimes
    2.45
    ilater
    2.45
    idy
    2.37
    orp
    2.34
    agos
    2.33
    enhagen
    2.32
    witz
    2.30
    asionally
    2.27
    gre
    2.27
    Act Density 0.000%

    No Known Activations