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

    Neuronpedia

    INDEX
    Explanations

    connective phrases indicating contrast or exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñħодим
    -0.12
    istributions
    -0.12
    ım
    -0.11
    .getElementsByClassName
    -0.11
    eldom
    -0.11
    óż
    -0.11
    %E
    -0.11
    %C
    -0.11
    ehler
    -0.11
    ģını
    -0.11
    POSITIVE LOGITS
     also
    1.11
    also
    0.98
    Also
    0.91
     Also
    0.91
     ALSO
    0.83
     también
    0.77
     também
    0.77
     juga
    0.77
     ÑĤакже
    0.76
     cũng
    0.73
    Act Density 1.763%

    No Known Activations