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

    Neuronpedia

    INDEX
    Explanations

    the presence of phrases indicating spending or financial exchanges

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

    instances of conjunctions and transitional phrases indicating connections between thoughts

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

    conjunctions and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roskov
    -0.51
     betweenstory
    -0.50
    huma
    -0.49
    ついに
    -0.49
    Хьажоргаш
    -0.49
    참고
    -0.47
     schließlich
    -0.47
     first
    -0.45
     Réalisation
    -0.45
     samples
    -0.43
    POSITIVE LOGITS
     hope
    0.85
     hoped
    0.72
    UseVisualStyle
    0.70
     EconPapers
    0.70
     hoppas
    0.70
     expect
    0.70
     Hopes
    0.69
     hoping
    0.69
     berharap
    0.68
     hoffen
    0.68
    Act Density 0.127%

    No Known Activations