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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transition phrases indicating contrast or change in argument

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

    contrastive conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.71
    出版年
    -0.59
     للمعارف
    -0.58
    exitRule
    -0.57
    OGND
    -0.54
     itſelf
    -0.53
     myſelf
    -0.52
    قایناقلار
    -0.50
    Fordítás
    -0.50
     Majefty
    -0.49
    POSITIVE LOGITS
    expandindo
    0.44
     nevertheless
    0.39
    TabIndex
    0.37
     nonetheless
    0.36
    LookAnd
    0.33
     tamen
    0.31
    ThroughAttribute
    0.31
     wensen
    0.31
     jednak
    0.30
    zeits
    0.29
    Act Density 0.039%

    No Known Activations