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

    Neuronpedia

    INDEX
    Explanations

    words indicating collaboration and interaction within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ervo
    -0.18
    igner
    -0.17
    £¼
    -0.17
    ÅĻÃŃzenÃŃ
    -0.16
    chwitz
    -0.16
    ERSHEY
    -0.16
    awei
    -0.15
    ernet
    -0.15
    (æľĪ
    -0.15
    è³Ģ
    -0.15
    POSITIVE LOGITS
    ating
    0.85
    ated
    0.83
    ation
    0.83
    ate
    0.68
    ator
    0.65
    ates
    0.65
    ators
    0.63
    ations
    0.62
    ative
    0.59
    ATING
    0.56
    Act Density 0.105%

    No Known Activations