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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apart
    -0.17
    ung
    -0.17
    ãģ°ãģĭãĤĬ
    -0.15
     Gerr
    -0.15
    ance
    -0.15
    ongyang
    -0.14
    tout
    -0.14
    ANJI
    -0.14
     kaz
    -0.14
    iqu
    -0.14
    POSITIVE LOGITS
     club
    0.25
     anyways
    0.22
    club
    0.20
     Club
    0.19
    Club
    0.18
    assa
    0.18
     anyway
    0.17
     Witness
    0.17
     witness
    0.17
     witnessing
    0.16
    Act Density 0.227%

    No Known Activations