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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and references to specific contexts or situations

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

    "however" or "but" followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    -0.71
     propOrder
    -0.65
    parsedMessage
    -0.59
    цездатний
    -0.59
    المناصب
    -0.55
    fromnode
    -0.55
    انيف
    -0.54
     macrop
    -0.54
    +#+#
    -0.54
     zove
    -0.53
    POSITIVE LOGITS
     húmedo
    0.47
    anmoins
    0.47
     kuitenkin
    0.46
     prisión
    0.45
     debido
    0.45
    retanto
    0.45
     mivel
    0.45
     jedoch
    0.44
     gesteld
    0.44
     desgracia
    0.43
    Act Density 0.033%

    No Known Activations