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

    Neuronpedia

    INDEX
    Explanations

    expressions of frustration or difficulties related to daily activities and experiences

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

    followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    special circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.72
     EconPapers
    -0.66
    AddAttribute
    -0.64
     ostavi
    -0.63
    ,:);
    -0.58
    FieldBuilder
    -0.58
     "..\..\
    -0.58
    OCCURRED
    -0.57
     Roskov
    -0.57
     "..\..\..\
    -0.55
    POSITIVE LOGITS
     nowadays
    1.00
    Especially
    0.83
     heut
    0.78
     Especially
    0.77
     especially
    0.72
     Nowadays
    0.68
    especially
    0.66
     sometimes
    0.64
    Nowadays
    0.63
     specialmente
    0.61
    Act Density 0.466%

    No Known Activations