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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating exclusion or differentiation from others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RunWith
    -0.48
     toalha
    -0.40
     Kearns
    -0.40
     with
    -0.40
     PNC
    -0.39
    一出
    -0.39
     Wilkinson
    -0.38
     by
    -0.36
     a
    -0.35
    MMP
    -0.35
    POSITIVE LOGITS
     else
    1.48
     Else
    1.45
    else
    1.41
     ELSE
    1.36
    Else
    1.31
    ELSE
    1.09
     Elsewhere
    0.88
    others
    0.86
     elsewhere
    0.84
    Elsewhere
    0.83
    Act Density 0.013%

    No Known Activations