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

    Neuronpedia

    INDEX
    Explanations

    expressions related to community and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    们
    -0.17
    ů
    -0.17
    s
    -0.15
    pagen
    -0.15
    outs
    -0.14
    enko
    -0.14
    aign
    -0.14
    ohn
    -0.14
    ajes
    -0.14
    aits
    -0.14
    POSITIVE LOGITS
    erto
    0.16
    ãģķãģ¾
    0.16
    ocab
    0.15
    stvo
    0.15
    iler
    0.15
    UILDER
    0.14
    ROTO
    0.14
    ominated
    0.14
    qd
    0.14
    ella
    0.14
    Act Density 0.482%

    No Known Activations