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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating affiliation or membership in organizations or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    äºĭæĥħ
    -0.15
    nger
    -0.14
    aña
    -0.14
    arsers
    -0.14
    ateria
    -0.14
     female
    -0.14
    irt
    -0.14
    ênh
    -0.13
    UIAlertAction
    -0.13
     Ratio
    -0.13
    POSITIVE LOGITS
     member
    0.25
     graduate
    0.24
     frequent
    0.22
     native
    0.21
     participant
    0.20
     frequ
    0.20
    graduate
    0.20
     sought
    0.19
     recipient
    0.19
    member
    0.19
    Act Density 0.079%

    No Known Activations