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

    Neuronpedia

    INDEX
    Explanations

    words related to community and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ("'"
    -0.17
    lu
    -0.15
    ucz
    -0.14
    аниÑĨ
    -0.13
     åı
    -0.13
    h
    -0.13
    eree
    -0.13
     dabei
    -0.13
    .enterprise
    -0.13
    primer
    -0.13
    POSITIVE LOGITS
     other
    0.20
     generally
    0.20
     otherwise
    0.19
    baar
    0.17
     such
    0.17
    other
    0.17
     sonst
    0.17
    otherwise
    0.16
     OTHERWISE
    0.16
    misc
    0.16
    Act Density 0.274%

    No Known Activations