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

    Neuronpedia

    INDEX
    Explanations

    words related to community involvement and collective actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampus
    -0.18
    artz
    -0.17
    loud
    -0.15
    صÙĪÙĦ
    -0.15
    enda
    -0.14
    apr
    -0.14
    orny
    -0.14
    oon
    -0.14
    ARP
    -0.14
     tÃŃch
    -0.14
    POSITIVE LOGITS
    ll
    0.26
     ll
    0.20
    roy
    0.20
    umb
    0.20
    llen
    0.18
    ouncill
    0.17
    ogra
    0.16
    ople
    0.15
     ult
    0.15
     roy
    0.15
    Act Density 0.011%

    No Known Activations