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

    Neuronpedia

    INDEX
    Explanations

    references to community or group identity and collective actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ela
    -0.17
    ãĥ¼ãĥ«
    -0.17
    ier
    -0.16
    ickness
    -0.16
    ng
    -0.15
    rys
    -0.15
    iero
    -0.15
    ensis
    -0.15
    ning
    -0.15
    essler
    -0.15
    POSITIVE LOGITS
    /group
    0.17
    tron
    0.16
    -sama
    0.15
    ì²´
    0.15
     opinion
    0.15
    HH
    0.14
     intelligence
    0.14
    /shared
    0.14
    ìĨį
    0.14
     effort
    0.14
    Act Density 0.020%

    No Known Activations