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

    Neuronpedia

    INDEX
    Explanations

    connectives and transitional phrases indicating logical relationships and arguments

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

    and, so, therefore connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     becauſe
    -0.56
     gynhyrchwyd
    -0.56
    __':
    -0.52
    __':
    -0.50
     hiszen
    -0.49
     Administrativna
    -0.49
    because
    -0.48
     pretože
    -0.46
    __":
    -0.46
     AssemblyCompany
    -0.46
    POSITIVE LOGITS
    дя
    0.39
     sli
    0.38
     soli
    0.38
     FetchType
    0.37
     fascin
    0.35
     HasFactory
    0.35
     Curi
    0.34
    ValueGeneration
    0.34
     upset
    0.33
     spe
    0.33
    Act Density 0.377%

    No Known Activations