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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and conditional phrases that indicate contrast or exception

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

    contrast and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    majánló
    -0.76
    itattu
    -0.76
    mpty
    -0.72
    ロウィン
    -0.71
     snippetHide
    -0.70
    iſen
    -0.68
     geſch
    -0.66
     Geiſt
    -0.66
    genodigd
    -0.65
    ulemon
    -0.65
    POSITIVE LOGITS
    ,
    0.73
    первых
    0.39
    Moreover
    0.37
     moreover
    0.36
     unfortunately
    0.36
     Moreover
    0.35
     however
    0.35
     있으며
    0.35
    ;
    0.34
     Asimismo
    0.34
    Act Density 0.010%

    No Known Activations