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

    Neuronpedia

    INDEX
    Explanations

    instances of contrastive conjunctions and qualifiers in the text

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

    but it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tit
    -0.43
    ContentAsync
    -0.39
     bog
    -0.38
    itäten
    -0.38
     sub
    -0.38
     Sub
    -0.37
    ModelBuilder
    -0.36
     mass
    -0.35
     puff
    -0.35
    ARTS
    -0.35
    POSITIVE LOGITS
     ब्रेकडाउन
    0.55
    migrationBuilder
    0.51
    NameInMap
    0.49
     становника
    0.47
     Italijanski
    0.46
     mensuales
    0.43
    httphttps
    0.43
     Infórmanos
    0.42
     Autres
    0.42
     aisladas
    0.42
    Act Density 0.366%

    No Known Activations